Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 287 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3054. Min Range: -8.3054
Max Act: 8.3054. Min Act: -0.1700
Data Index: 4434750 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3054. Min Range: -8.3054
Max Act: 8.0554. Min Act: -0.1700
Data Index: 5719064 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.7429. Min Act: -0.1700
Data Index: 3510086 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.7429. Min Act: -0.1700
Data Index: 2636683 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.6804. Min Act: -0.1700
Data Index: 8337957 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.6804. Min Act: -0.1700
Data Index: 4192723 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.5554. Min Act: -0.1700
Data Index: 5472464 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.5866. Min Act: -0.1700
Data Index: 6151750 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.5241. Min Act: -0.1700
Data Index: 855655 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.5241. Min Act: -0.1700
Data Index: 6383549 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.4616. Min Act: -0.1700
Data Index: 4247260 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.4616. Min Act: -0.1700
Data Index: 5110462 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3991. Min Act: -0.1700
Data Index: 8664696 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3991. Min Act: -0.1700
Data Index: 7078985 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3991. Min Act: -0.1700
Data Index: 4971136 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3991. Min Act: -0.1700
Data Index: 3492793 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3991. Min Act: -0.1700
Data Index: 7576377 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3679. Min Act: -0.1700
Data Index: 3043146 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3679. Min Act: -0.1700
Data Index: 7682132 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3054. Min Range: -8.3054
Max Act: 7.3366. Min Act: -0.1700
Data Index: 1526675 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19