Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 21.3724. Min Range: -21.3724
Max Act: 21.3724. Min Act: -0.1700
Data Index: 3363638 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.9974. Min Act: -0.1700
Data Index: 2664118 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.3724. Min Range: -21.3724
Max Act: 21.1224. Min Act: -0.1700
Data Index: 1966881 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.9974. Min Act: -0.1700
Data Index: 3857572 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.9974. Min Act: -0.1700
Data Index: 462274 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.7474. Min Act: -0.1700
Data Index: 4194774 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.8724. Min Act: -0.1700
Data Index: 8037284 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.6224. Min Act: -0.1700
Data Index: 6161194 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.6224. Min Act: -0.1700
Data Index: 3171377 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.7474. Min Act: -0.1700
Data Index: 4816758 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.6224. Min Act: -0.1700
Data Index: 8211528 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.7474. Min Act: -0.1700
Data Index: 8230179 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.4974. Min Act: -0.1700
Data Index: 7958506 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.7474. Min Act: -0.1700
Data Index: 98253 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.7474. Min Act: -0.1700
Data Index: 6027884 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.6224. Min Act: -0.1700
Data Index: 4876995 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.2474. Min Act: -0.1700
Data Index: 6321712 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.4974. Min Act: -0.1700
Data Index: 3148711 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.4974. Min Act: -0.1700
Data Index: 5982264 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.3724. Min Range: -21.3724
Max Act: 20.3724. Min Act: -0.1700
Data Index: 5795914 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19