Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.7394. Min Act: -0.1700
Data Index: 3395050 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.5207. Min Act: -0.1700
Data Index: 8526842 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.5207. Min Act: -0.1700
Data Index: 7647253 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.4582. Min Act: -0.1700
Data Index: 7845057 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.4582. Min Act: -0.1700
Data Index: 4003073 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.4582. Min Act: -0.1700
Data Index: 2634376 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.4269. Min Act: -0.1700
Data Index: 3399473 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3957. Min Act: -0.1700
Data Index: 6167249 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3957. Min Act: -0.1700
Data Index: 6026324 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3644. Min Act: -0.1700
Data Index: 730410 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3957. Min Act: -0.1700
Data Index: 8648486 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3644. Min Act: -0.1700
Data Index: 3164278 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3644. Min Act: -0.1700
Data Index: 310932 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3644. Min Act: -0.1700
Data Index: 324890 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3644. Min Act: -0.1700
Data Index: 176871 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3644. Min Act: -0.1700
Data Index: 2123918 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3957. Min Act: -0.1700
Data Index: 7389099 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6895366 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3332. Min Act: -0.1700
Data Index: 1195100 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7394. Min Range: -6.7394
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6395819 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19