Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.6434. Min Act: -0.1700
Data Index: 8111247 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.6434. Min Act: -0.1700
Data Index: 7750311 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.5809. Min Act: -0.1700
Data Index: 4631332 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.6122. Min Act: -0.1700
Data Index: 4275483 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.5809. Min Act: -0.1700
Data Index: 7672901 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.5809. Min Act: -0.1700
Data Index: 4778354 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.5184. Min Act: -0.1700
Data Index: 4506675 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4872. Min Act: -0.1700
Data Index: 6137593 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4872. Min Act: -0.1699
Data Index: 3358042 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4872. Min Act: -0.1700
Data Index: 2511117 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4559. Min Act: -0.1700
Data Index: 1418589 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4559. Min Act: -0.1700
Data Index: 3869676 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4559. Min Act: -0.1700
Data Index: 4036290 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4559. Min Act: -0.1700
Data Index: 1127034 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4559. Min Act: -0.1700
Data Index: 6671994 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4247. Min Act: -0.1700
Data Index: 3553046 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4247. Min Act: -0.1700
Data Index: 7435093 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4559. Min Act: -0.1700
Data Index: 2076866 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4247. Min Act: -0.1700
Data Index: 1856661 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6434. Min Range: -5.6434
Max Act: 5.4247. Min Act: -0.1700
Data Index: 7395087 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19