Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3819 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0684. Min Range: -7.0684
Max Act: 7.0684. Min Act: -0.1700
Data Index: 3796999 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0684. Min Range: -7.0684
Max Act: 7.0059. Min Act: -0.1700
Data Index: 4190073 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.8184. Min Act: -0.1700
Data Index: 1578597 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.7559. Min Act: -0.1700
Data Index: 6659710 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.7559. Min Act: -0.1700
Data Index: 281015 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.7247. Min Act: -0.1700
Data Index: 5529696 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.7247. Min Act: -0.1700
Data Index: 3187213 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.5372. Min Act: -0.1700
Data Index: 2359237 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.5372. Min Act: -0.1700
Data Index: 949163 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.5372. Min Act: -0.1700
Data Index: 1458770 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.5059. Min Act: -0.1700
Data Index: 5043868 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.5059. Min Act: -0.1700
Data Index: 1000272 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.5059. Min Act: -0.1700
Data Index: 6128579 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.4747. Min Act: -0.1700
Data Index: 3962887 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.4747. Min Act: -0.1700
Data Index: 6138222 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.4434. Min Act: -0.1700
Data Index: 8349129 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.4434. Min Act: -0.1700
Data Index: 4160007 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.4434. Min Act: -0.1700
Data Index: 1527368 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.4434. Min Act: -0.1700
Data Index: 545512 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0684. Min Range: -7.0684
Max Act: 6.4122. Min Act: -0.1700
Data Index: 6523399 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19