Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3324 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.7030. Min Act: -0.1700
Data Index: 3664968 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.5780. Min Act: -0.1700
Data Index: 6722097 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.3905. Min Act: -0.1700
Data Index: 2498015 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.3592. Min Act: -0.1700
Data Index: 1456790 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.2967. Min Act: -0.1700
Data Index: 1293602 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.2030. Min Act: -0.1700
Data Index: 5332214 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.2342. Min Act: -0.1700
Data Index: 5137732 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.1405. Min Act: -0.1700
Data Index: 1073835 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.1405. Min Act: -0.1700
Data Index: 7531455 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.0155. Min Act: -0.1700
Data Index: 2475838 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.0155. Min Act: -0.1700
Data Index: 405564 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9842. Min Act: -0.1700
Data Index: 696461 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9842. Min Act: -0.1700
Data Index: 3571628 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7030. Min Range: -7.7030
Max Act: 7.0155. Min Act: -0.1700
Data Index: 8203667 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9842. Min Act: -0.1700
Data Index: 875359 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9842. Min Act: -0.1700
Data Index: 7679225 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9530. Min Act: -0.1700
Data Index: 7050377 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9530. Min Act: -0.1700
Data Index: 44938 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9530. Min Act: -0.1700
Data Index: 5203901 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7030. Min Range: -7.7030
Max Act: 6.9530. Min Act: -0.1700
Data Index: 1289453 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19