Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5458. Min Range: -6.5458
Max Act: 6.5458. Min Act: -0.1700
Data Index: 5866969 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5458. Min Range: -6.5458
Max Act: 6.4521. Min Act: -0.1700
Data Index: 7528342 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5458. Min Range: -6.5458
Max Act: 6.2646. Min Act: -0.1700
Data Index: 2091930 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5458. Min Range: -6.5458
Max Act: 6.0771. Min Act: -0.1700
Data Index: 830267 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5458. Min Range: -6.5458
Max Act: 6.1083. Min Act: -0.1700
Data Index: 434016 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5458. Min Range: -6.5458
Max Act: 6.0146. Min Act: -0.1700
Data Index: 3427275 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.9833. Min Act: -0.1700
Data Index: 8452313 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.9521. Min Act: -0.1700
Data Index: 6984588 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.9521. Min Act: -0.1700
Data Index: 2983504 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.9521. Min Act: -0.1700
Data Index: 5086790 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.8896. Min Act: -0.1700
Data Index: 6323389 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.9208. Min Act: -0.1700
Data Index: 5766457 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.8896. Min Act: -0.1700
Data Index: 4866687 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.8583. Min Act: -0.1700
Data Index: 3611832 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.8583. Min Act: -0.1700
Data Index: 4215682 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.8271. Min Act: -0.1700
Data Index: 6865423 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.8271. Min Act: -0.1700
Data Index: 7142492 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.8271. Min Act: -0.1700
Data Index: 6851414 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.7958. Min Act: -0.1700
Data Index: 1582016 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5458. Min Range: -6.5458
Max Act: 5.7958. Min Act: -0.1700
Data Index: 1783388 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19