Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.6595. Min Act: -0.1700
Data Index: 5037628 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.6595. Min Act: -0.1700
Data Index: 4754308 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.6595. Min Act: -0.1700
Data Index: 992393 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.6595. Min Act: -0.1700
Data Index: 992399 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.5657. Min Act: -0.1700
Data Index: 992400 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.5345. Min Act: -0.1700
Data Index: 4754294 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.5032. Min Act: -0.1700
Data Index: 2195949 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.5032. Min Act: -0.1700
Data Index: 992394 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.5032. Min Act: -0.1700
Data Index: 5037613 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.4720. Min Act: -0.1700
Data Index: 4943036 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.4720. Min Act: -0.1700
Data Index: 8195430 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.4407. Min Act: -0.1700
Data Index: 5037627 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.4407. Min Act: -0.1700
Data Index: 5037612 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.3782. Min Act: -0.1700
Data Index: 992398 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.3470. Min Act: -0.1700
Data Index: 3777807 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.3782. Min Act: -0.1700
Data Index: 3401007 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.3470. Min Act: -0.1700
Data Index: 2195920 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.3470. Min Act: -0.1700
Data Index: 3101753 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.3470. Min Act: -0.1700
Data Index: 2328430 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6595. Min Range: -5.6595
Max Act: 5.3157. Min Act: -0.1700
Data Index: 2011708 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19