Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 718 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2227. Min Range: -9.2227
Max Act: 9.2227. Min Act: -0.1700
Data Index: 3094548 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.9727. Min Act: -0.1700
Data Index: 3782216 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.9727. Min Act: -0.1700
Data Index: 2236563 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.9102. Min Act: -0.1700
Data Index: 6607394 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.7852. Min Act: -0.1700
Data Index: 2495491 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.7852. Min Act: -0.1700
Data Index: 8522587 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.7227. Min Act: -0.1700
Data Index: 5451094 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.7227. Min Act: -0.1700
Data Index: 4047001 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.6602. Min Act: -0.1700
Data Index: 855773 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.6602. Min Act: -0.1700
Data Index: 2093001 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.6602. Min Act: -0.1700
Data Index: 1295093 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.6602. Min Act: -0.1700
Data Index: 5231676 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.6602. Min Act: -0.1700
Data Index: 1221848 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.5352. Min Act: -0.1698
Data Index: 7190875 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.5977. Min Act: -0.1700
Data Index: 2431378 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.5977. Min Act: -0.1700
Data Index: 8029503 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.5977. Min Act: -0.1700
Data Index: 811541 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.5977. Min Act: -0.1700
Data Index: 6064229 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.5977. Min Act: -0.1700
Data Index: 6564121 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2227. Min Range: -9.2227
Max Act: 8.5352. Min Act: -0.1700
Data Index: 6607391 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19