Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2238. Min Range: -6.2238
Max Act: 6.2238. Min Act: -0.1700
Data Index: 6019349 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2238. Min Range: -6.2238
Max Act: 6.2238. Min Act: -0.1700
Data Index: 6616918 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.9738. Min Act: -0.1700
Data Index: 3154814 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.8800. Min Act: -0.1700
Data Index: 4604284 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.8800. Min Act: -0.1700
Data Index: 8228482 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.7863. Min Act: -0.1700
Data Index: 6984800 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.7863. Min Act: -0.1700
Data Index: 1270004 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6925. Min Act: -0.1700
Data Index: 5654698 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.7238. Min Act: -0.1700
Data Index: 6510437 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6925. Min Act: -0.1700
Data Index: 1147187 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6300. Min Act: -0.1700
Data Index: 3495574 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6613. Min Act: -0.1700
Data Index: 2815193 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6613. Min Act: -0.1700
Data Index: 5318049 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6613. Min Act: -0.1700
Data Index: 3199554 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6613. Min Act: -0.1700
Data Index: 1968855 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6300. Min Act: -0.1700
Data Index: 5371998 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6300. Min Act: -0.1700
Data Index: 4614253 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.6300. Min Act: -0.1700
Data Index: 892628 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.5988. Min Act: -0.1700
Data Index: 603286 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2238. Min Range: -6.2238
Max Act: 5.5988. Min Act: -0.1700
Data Index: 7416368 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19