Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.2176. Min Act: -0.1700
Data Index: 1548969 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.1864. Min Act: -0.1700
Data Index: 7750884 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.1864. Min Act: -0.1700
Data Index: 555994 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.1864. Min Act: -0.1700
Data Index: 3133533 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.1239. Min Act: -0.1700
Data Index: 1707829 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.0926. Min Act: -0.1700
Data Index: 4872733 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.1239. Min Act: -0.1700
Data Index: 1704437 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2176. Min Range: -6.2176
Max Act: 6.0301. Min Act: -0.1700
Data Index: 40046 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9989. Min Act: -0.1700
Data Index: 4224756 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9989. Min Act: -0.1700
Data Index: 4267543 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9676. Min Act: -0.1700
Data Index: 8696538 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9676. Min Act: -0.1700
Data Index: 7734725 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9676. Min Act: -0.1700
Data Index: 8161199 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9364. Min Act: -0.1700
Data Index: 5666274 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9364. Min Act: -0.1700
Data Index: 5275334 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9364. Min Act: -0.1700
Data Index: 6002677 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9051. Min Act: -0.1700
Data Index: 6107585 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.9051. Min Act: -0.1700
Data Index: 4448423 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.8739. Min Act: -0.1700
Data Index: 5641411 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2176. Min Range: -6.2176
Max Act: 5.8426. Min Act: -0.1700
Data Index: 4649389 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19