Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 461 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.9602. Min Act: -0.1700
Data Index: 2384236 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.6165. Min Act: -0.1700
Data Index: 6386308 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.5852. Min Act: -0.1700
Data Index: 2622990 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.6165. Min Act: -0.1700
Data Index: 2343723 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.5227. Min Act: -0.1700
Data Index: 5336362 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.5540. Min Act: -0.1700
Data Index: 6650386 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.4915. Min Act: -0.1700
Data Index: 8555234 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.4290. Min Act: -0.1700
Data Index: 3732815 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.4290. Min Act: -0.1700
Data Index: 3804694 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.4290. Min Act: -0.1700
Data Index: 109244 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3977. Min Act: -0.1700
Data Index: 3733020 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3977. Min Act: -0.1700
Data Index: 3964546 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3977. Min Act: -0.1700
Data Index: 4455198 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3977. Min Act: -0.1700
Data Index: 2484498 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3977. Min Act: -0.1700
Data Index: 2455771 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3665. Min Act: -0.1700
Data Index: 3489995 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3977. Min Act: -0.1700
Data Index: 5641334 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3665. Min Act: -0.1700
Data Index: 2304491 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3665. Min Act: -0.1700
Data Index: 959847 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9602. Min Range: -5.9602
Max Act: 5.3665. Min Act: -0.1700
Data Index: 5419210 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19