Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.1332. Min Act: -0.1700
Data Index: 4758802 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.1019. Min Act: -0.1700
Data Index: 29805 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.1019. Min Act: -0.1700
Data Index: 5890714 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0707. Min Act: -0.1700
Data Index: 5678412 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0707. Min Act: -0.1700
Data Index: 6832554 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0707. Min Act: -0.1700
Data Index: 8380464 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0707. Min Act: -0.1700
Data Index: 927792 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0394. Min Act: -0.1700
Data Index: 1255599 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0394. Min Act: -0.1700
Data Index: 1625816 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0394. Min Act: -0.1700
Data Index: 2282824 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0394. Min Act: -0.1700
Data Index: 542053 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0394. Min Act: -0.1700
Data Index: 2086781 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0394. Min Act: -0.1700
Data Index: 5470516 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0082. Min Act: -0.1700
Data Index: 8327756 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1332. Min Range: -6.1332
Max Act: 6.0082. Min Act: -0.1700
Data Index: 7167762 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1332. Min Range: -6.1332
Max Act: 5.9769. Min Act: -0.1700
Data Index: 4997933 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1332. Min Range: -6.1332
Max Act: 5.9144. Min Act: -0.1700
Data Index: 3293399 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1332. Min Range: -6.1332
Max Act: 5.9457. Min Act: -0.1700
Data Index: 6709464 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1332. Min Range: -6.1332
Max Act: 5.9457. Min Act: -0.1700
Data Index: 4310041 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1332. Min Range: -6.1332
Max Act: 5.9457. Min Act: -0.1700
Data Index: 4276275 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19