Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.9355. Min Act: -0.1700
Data Index: 8643461 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.9355. Min Act: -0.1700
Data Index: 5913593 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.8105. Min Act: -0.1700
Data Index: 7865038 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.7480. Min Act: -0.1700
Data Index: 2552291 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1507154 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.6855. Min Act: -0.1700
Data Index: 7098435 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.6855. Min Act: -0.1700
Data Index: 8645645 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.6542. Min Act: -0.1700
Data Index: 2257145 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.6230. Min Act: -0.1700
Data Index: 4565493 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5917. Min Act: -0.1700
Data Index: 6994252 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5917. Min Act: -0.1700
Data Index: 3198053 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5917. Min Act: -0.1700
Data Index: 8421001 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5917. Min Act: -0.1700
Data Index: 1192755 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5917. Min Act: -0.1700
Data Index: 3984580 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5605. Min Act: -0.1700
Data Index: 2426113 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5605. Min Act: -0.1700
Data Index: 7594841 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5292. Min Act: -0.1700
Data Index: 3958820 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5292. Min Act: -0.1700
Data Index: 1957895 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5292. Min Act: -0.1700
Data Index: 3720496 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.4980. Min Act: -0.1700
Data Index: 1444710 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19