Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3337 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.7055. Min Act: -0.1700
Data Index: 549203 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.6742. Min Act: -0.1700
Data Index: 3187500 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.5805. Min Act: -0.1700
Data Index: 4928073 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.6430. Min Act: -0.1700
Data Index: 7204479 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.5492. Min Act: -0.1700
Data Index: 7606134 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.5492. Min Act: -0.1700
Data Index: 7541821 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.5180. Min Act: -0.1700
Data Index: 8289509 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.5180. Min Act: -0.1700
Data Index: 6349261 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4867. Min Act: -0.1700
Data Index: 7180521 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4867. Min Act: -0.1700
Data Index: 4044165 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4555. Min Act: -0.1700
Data Index: 4982092 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4867. Min Act: -0.1700
Data Index: 2337186 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4555. Min Act: -0.1700
Data Index: 5933301 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4555. Min Act: -0.1700
Data Index: 1291224 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4555. Min Act: -0.1700
Data Index: 2129915 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4242. Min Act: -0.1700
Data Index: 5970316 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4242. Min Act: -0.1700
Data Index: 335682 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.3930. Min Act: -0.1700
Data Index: 3948606 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.4242. Min Act: -0.1700
Data Index: 1841595 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.3930. Min Act: -0.1700
Data Index: 2720941 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19