Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2419 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.2769. Min Act: -0.1700
Data Index: 1771036 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.2455. Min Act: -0.1700
Data Index: 106556 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.2140. Min Act: -0.1700
Data Index: 6724680 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1983. Min Act: -0.1700
Data Index: 1365806 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1669. Min Act: -0.1700
Data Index: 7678692 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1354. Min Act: -0.1700
Data Index: 4112516 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1196. Min Act: -0.1700
Data Index: 2309761 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1511. Min Act: -0.1700
Data Index: 5173257 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1354. Min Act: -0.1700
Data Index: 6273566 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1354. Min Act: -0.1700
Data Index: 634816 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1196. Min Act: -0.1700
Data Index: 3638484 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1039. Min Act: -0.1700
Data Index: 2928961 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1196. Min Act: -0.1700
Data Index: 2813172 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1039. Min Act: -0.1700
Data Index: 7097686 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1039. Min Act: -0.1700
Data Index: 7310057 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.0881. Min Act: -0.1700
Data Index: 4328399 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.0881. Min Act: -0.1700
Data Index: 1109575 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.0723. Min Act: -0.1700
Data Index: 4195763 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.0881. Min Act: -0.1700
Data Index: 7915774 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2769. Min Range: -3.2769
Max Act: 3.1039. Min Act: -0.1700
Data Index: 3620551 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19