Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0497. Min Range: -10.0497
Max Act: 10.0497. Min Act: -0.1700
Data Index: 4609276 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.9247. Min Act: -0.1700
Data Index: 278593 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.8622. Min Act: -0.1700
Data Index: 8240426 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.7997. Min Act: -0.1700
Data Index: 69955 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.7372. Min Act: -0.1700
Data Index: 8161364 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.7997. Min Act: -0.1700
Data Index: 4892734 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.7372. Min Act: -0.1700
Data Index: 791110 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.7372. Min Act: -0.1700
Data Index: 3943349 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.7372. Min Act: -0.1700
Data Index: 1404002 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.7372. Min Act: -0.1699
Data Index: 5559984 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.6747. Min Act: -0.1700
Data Index: 459590 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.6122. Min Act: -0.1700
Data Index: 4171376 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.5497. Min Act: -0.1700
Data Index: 829125 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.5497. Min Act: -0.1700
Data Index: 7726649 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.5497. Min Act: -0.1700
Data Index: 2459058 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.5497. Min Act: -0.1700
Data Index: 1227807 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.4247. Min Act: -0.1700
Data Index: 1026884 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.4872. Min Act: -0.1700
Data Index: 1672866 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.4247. Min Act: -0.1700
Data Index: 432448 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0497. Min Range: -10.0497
Max Act: 8.3622. Min Act: -0.1700
Data Index: 6958658 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19