Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6064. Min Range: -9.6064
Max Act: 9.6064. Min Act: -0.1700
Data Index: 5074506 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6064. Min Range: -9.6064
Max Act: 9.4814. Min Act: -0.1700
Data Index: 1836392 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6064. Min Range: -9.6064
Max Act: 9.2939. Min Act: -0.1700
Data Index: 3179305 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6064. Min Range: -9.6064
Max Act: 9.1689. Min Act: -0.1700
Data Index: 1292323 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.9814. Min Act: -0.1700
Data Index: 8170206 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.8564. Min Act: -0.1700
Data Index: 1768967 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.7939. Min Act: -0.1700
Data Index: 4226749 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.7939. Min Act: -0.1700
Data Index: 6296318 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.7314. Min Act: -0.1700
Data Index: 7881478 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.6064. Min Act: -0.1700
Data Index: 5242217 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.6064. Min Act: -0.1700
Data Index: 4081303 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.5439. Min Act: -0.1700
Data Index: 4318087 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.5439. Min Act: -0.1700
Data Index: 2267132 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.4814. Min Act: -0.1700
Data Index: 1628025 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.4189. Min Act: -0.1700
Data Index: 4958854 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.4189. Min Act: -0.1700
Data Index: 5585690 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.3564. Min Act: -0.1700
Data Index: 683033 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.3564. Min Act: -0.1700
Data Index: 6532323 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.2939. Min Act: -0.1700
Data Index: 2276211 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6064. Min Range: -9.6064
Max Act: 8.3564. Min Act: -0.1700
Data Index: 672872 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19