Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.5614. Min Act: -0.1700
Data Index: 8227412 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.5614. Min Act: -0.1700
Data Index: 4768305 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.4989. Min Act: -0.1700
Data Index: 159604 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.4676. Min Act: -0.1700
Data Index: 3963547 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.4051. Min Act: -0.1700
Data Index: 1182055 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.4051. Min Act: -0.1700
Data Index: 8053522 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.4051. Min Act: -0.1700
Data Index: 3953080 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3739. Min Act: -0.1700
Data Index: 1866856 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3739. Min Act: -0.1700
Data Index: 5812273 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3426. Min Act: -0.1700
Data Index: 5976498 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3426. Min Act: -0.1700
Data Index: 1268448 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3426. Min Act: -0.1700
Data Index: 3528480 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3114. Min Act: -0.1700
Data Index: 2251598 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3114. Min Act: -0.1700
Data Index: 3989135 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3114. Min Act: -0.1700
Data Index: 3998379 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.3114. Min Act: -0.1700
Data Index: 7712324 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.2801. Min Act: -0.1700
Data Index: 4940058 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.2801. Min Act: -0.1700
Data Index: 6444709 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.2801. Min Act: -0.1700
Data Index: 6258453 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5614. Min Range: -5.5614
Max Act: 5.2489. Min Act: -0.1700
Data Index: 3998378 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19