Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6462. Min Range: -8.6462
Max Act: 8.6462. Min Act: -0.1700
Data Index: 7174821 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6462. Min Range: -8.6462
Max Act: 8.3337. Min Act: -0.1700
Data Index: 7187513 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6462. Min Range: -8.6462
Max Act: 8.0837. Min Act: -0.1700
Data Index: 6751185 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6462. Min Range: -8.6462
Max Act: 8.0212. Min Act: -0.1700
Data Index: 605819 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6462. Min Range: -8.6462
Max Act: 8.0212. Min Act: -0.1700
Data Index: 6337042 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.9587. Min Act: -0.1700
Data Index: 854555 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.9587. Min Act: -0.1700
Data Index: 3882539 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.8962. Min Act: -0.1700
Data Index: 5593620 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.8962. Min Act: -0.1700
Data Index: 3471522 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.8962. Min Act: -0.1700
Data Index: 6639810 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.8337. Min Act: -0.1700
Data Index: 3575094 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.8337. Min Act: -0.1700
Data Index: 2177696 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.7712. Min Act: -0.1700
Data Index: 4770490 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.7712. Min Act: -0.1700
Data Index: 526482 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.7712. Min Act: -0.1700
Data Index: 3935997 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.7712. Min Act: -0.1700
Data Index: 833754 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.7087. Min Act: -0.1700
Data Index: 5478701 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.7087. Min Act: -0.1700
Data Index: 2266823 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.6462. Min Act: -0.1700
Data Index: 3905208 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6462. Min Range: -8.6462
Max Act: 7.6462. Min Act: -0.1700
Data Index: 1613148 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19