Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.7169. Min Act: -0.1700
Data Index: 1440501 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.6857. Min Act: -0.1700
Data Index: 8702199 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.4044. Min Act: -0.1700
Data Index: 7077734 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.3732. Min Act: -0.1700
Data Index: 5306660 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.2482. Min Act: -0.1700
Data Index: 2347643 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.2169. Min Act: -0.1700
Data Index: 817478 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.2169. Min Act: -0.1700
Data Index: 3771418 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.2169. Min Act: -0.1700
Data Index: 2337160 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.1857. Min Act: -0.1700
Data Index: 808826 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.1857. Min Act: -0.1700
Data Index: 760696 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.1857. Min Act: -0.1700
Data Index: 507188 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.1544. Min Act: -0.1700
Data Index: 2986587 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.1232. Min Act: -0.1700
Data Index: 6515107 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.0607. Min Act: -0.1700
Data Index: 2828536 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.0294. Min Act: -0.1700
Data Index: 7987349 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.0294. Min Act: -0.1700
Data Index: 5830448 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7169. Min Range: -7.7169
Max Act: 7.0294. Min Act: -0.1700
Data Index: 109397 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7169. Min Range: -7.7169
Max Act: 6.9982. Min Act: -0.1700
Data Index: 7611174 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7169. Min Range: -7.7169
Max Act: 6.9669. Min Act: -0.1700
Data Index: 2805749 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7169. Min Range: -7.7169
Max Act: 6.9669. Min Act: -0.1700
Data Index: 8457430 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19