Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.9505. Min Act: -0.1700
Data Index: 3727383 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.9192. Min Act: -0.1700
Data Index: 6683176 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.9192. Min Act: -0.1700
Data Index: 7969817 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.8880. Min Act: -0.1700
Data Index: 1094908 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.6067. Min Act: -0.1700
Data Index: 2043954 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.5442. Min Act: -0.1700
Data Index: 4699342 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.5130. Min Act: -0.1700
Data Index: 6095164 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.4817. Min Act: -0.1700
Data Index: 2348307 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.4817. Min Act: -0.1700
Data Index: 2976874 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.4192. Min Act: -0.1700
Data Index: 8714542 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.3880. Min Act: -0.1700
Data Index: 2469481 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.3567. Min Act: -0.1700
Data Index: 8200233 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.3880. Min Act: -0.1700
Data Index: 3247241 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.3880. Min Act: -0.1700
Data Index: 2846266 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.3880. Min Act: -0.1700
Data Index: 245594 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.3567. Min Act: -0.1700
Data Index: 4959927 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.3567. Min Act: -0.1700
Data Index: 2597481 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.2942. Min Act: -0.1700
Data Index: 2577107 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.2942. Min Act: -0.1700
Data Index: 6095165 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9505. Min Range: -7.9505
Max Act: 7.2630. Min Act: -0.1700
Data Index: 3056629 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19