Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.5802. Min Act: -0.1700
Data Index: 4518999 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.4240. Min Act: -0.1700
Data Index: 94624 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.2677. Min Act: -0.1700
Data Index: 3181762 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.2052. Min Act: -0.1700
Data Index: 4117372 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.2365. Min Act: -0.1700
Data Index: 2108920 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.1740. Min Act: -0.1700
Data Index: 831973 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.1740. Min Act: -0.1700
Data Index: 5979099 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.1427. Min Act: -0.1700
Data Index: 128820 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.1427. Min Act: -0.1700
Data Index: 2214051 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.1115. Min Act: -0.1700
Data Index: 2489274 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.0490. Min Act: -0.1700
Data Index: 3890732 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.0490. Min Act: -0.1700
Data Index: 1104399 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.0490. Min Act: -0.1700
Data Index: 7963440 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.0490. Min Act: -0.1700
Data Index: 8367266 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.0177. Min Act: -0.1700
Data Index: 2062669 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5802. Min Range: -7.5802
Max Act: 6.9865. Min Act: -0.1700
Data Index: 2402458 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5802. Min Range: -7.5802
Max Act: 6.9865. Min Act: -0.1700
Data Index: 7542561 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5802. Min Range: -7.5802
Max Act: 6.9865. Min Act: -0.1700
Data Index: 1709730 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5802. Min Range: -7.5802
Max Act: 6.9865. Min Act: -0.1700
Data Index: 3873403 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5802. Min Range: -7.5802
Max Act: 7.0177. Min Act: -0.1700
Data Index: 3868387 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19