Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 986 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.9140. Min Act: -0.1700
Data Index: 5021062 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.4765. Min Act: -0.1700
Data Index: 5256445 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.4765. Min Act: -0.1700
Data Index: 566844 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.3515. Min Act: -0.1700
Data Index: 6132881 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2890. Min Act: -0.1700
Data Index: 3862074 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2265. Min Act: -0.1700
Data Index: 5549763 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2578. Min Act: -0.1700
Data Index: 1899207 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2265. Min Act: -0.1700
Data Index: 3420253 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2578. Min Act: -0.1700
Data Index: 6842704 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2578. Min Act: -0.1700
Data Index: 1776467 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2265. Min Act: -0.1700
Data Index: 4492116 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1953. Min Act: -0.1700
Data Index: 3899842 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1953. Min Act: -0.1700
Data Index: 6940348 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1953. Min Act: -0.1700
Data Index: 7729288 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.2265. Min Act: -0.1700
Data Index: 8544892 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1953. Min Act: -0.1700
Data Index: 4802893 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1953. Min Act: -0.1700
Data Index: 650812 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1953. Min Act: -0.1700
Data Index: 4273613 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1640. Min Act: -0.1700
Data Index: 7471197 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9140. Min Range: -5.9140
Max Act: 5.1640. Min Act: -0.1700
Data Index: 5670432 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19