Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4165 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 5575839 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.4022. Min Act: -0.1700
Data Index: 3789588 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.3397. Min Act: -0.1700
Data Index: 3414996 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.4022. Min Act: -0.1700
Data Index: 7224959 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.2772. Min Act: -0.1700
Data Index: 8257531 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.2772. Min Act: -0.1700
Data Index: 1935399 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.2772. Min Act: -0.1700
Data Index: 2724804 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.2772. Min Act: -0.1700
Data Index: 3479960 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.2147. Min Act: -0.1700
Data Index: 6670229 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.2147. Min Act: -0.1700
Data Index: 6894817 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.2147. Min Act: -0.1700
Data Index: 2558270 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.1522. Min Act: -0.1700
Data Index: 971946 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0897. Min Act: -0.1700
Data Index: 6486503 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0897. Min Act: -0.1700
Data Index: 8178753 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0897. Min Act: -0.1700
Data Index: 7847347 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0897. Min Act: -0.1700
Data Index: 1894407 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0272. Min Act: -0.1700
Data Index: 1008975 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0272. Min Act: -0.1700
Data Index: 3689885 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0272. Min Act: -0.1700
Data Index: 7344089 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9647. Min Range: -8.9647
Max Act: 8.0272. Min Act: -0.1700
Data Index: 1651853 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19