Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3697 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1454. Min Range: -3.1454
Max Act: 3.1454. Min Act: -0.1700
Data Index: 2539903 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1454. Min Range: -3.1454
Max Act: 3.0193. Min Act: -0.1700
Data Index: 1624077 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1454. Min Range: -3.1454
Max Act: 3.0035. Min Act: -0.1700
Data Index: 5316603 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9719. Min Act: -0.1700
Data Index: 4402750 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9402. Min Act: -0.1700
Data Index: 8755069 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9561. Min Act: -0.1700
Data Index: 1230611 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9561. Min Act: -0.1700
Data Index: 5552803 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9402. Min Act: -0.1700
Data Index: 8109820 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9085. Min Act: -0.1700
Data Index: 6204855 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9244. Min Act: -0.1700
Data Index: 2559276 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9244. Min Act: -0.1700
Data Index: 943217 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9244. Min Act: -0.1700
Data Index: 2875494 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9244. Min Act: -0.1700
Data Index: 5235860 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9402. Min Act: -0.1700
Data Index: 4921321 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8927. Min Act: -0.1700
Data Index: 2365022 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8927. Min Act: -0.1700
Data Index: 7928434 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8927. Min Act: -0.1700
Data Index: 3368717 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8927. Min Act: -0.1700
Data Index: 3218288 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8927. Min Act: -0.1700
Data Index: 6465157 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8927. Min Act: -0.1700
Data Index: 8329422 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19