Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.0681. Min Range: -12.0681
Max Act: 12.0681. Min Act: -0.1700
Data Index: 1624807 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.8806. Min Act: -0.1700
Data Index: 8248396 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.7556. Min Act: -0.1700
Data Index: 1737389 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.7556. Min Act: -0.1700
Data Index: 8630266 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.6931. Min Act: -0.1700
Data Index: 2267903 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5681. Min Act: -0.1700
Data Index: 4314730 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.6306. Min Act: -0.1700
Data Index: 4675546 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.6306. Min Act: -0.1700
Data Index: 2606496 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.6306. Min Act: -0.1700
Data Index: 5428502 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5056. Min Act: -0.1700
Data Index: 4530034 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5681. Min Act: -0.1700
Data Index: 5010 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5056. Min Act: -0.1700
Data Index: 5428503 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5056. Min Act: -0.1700
Data Index: 7760792 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5056. Min Act: -0.1700
Data Index: 7727032 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5681. Min Act: -0.1700
Data Index: 8577700 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.5681. Min Act: -0.1700
Data Index: 395023 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.4431. Min Act: -0.1700
Data Index: 5300494 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.3181. Min Act: -0.1700
Data Index: 1919467 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.3806. Min Act: -0.1700
Data Index: 2957320 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0681. Min Range: -12.0681
Max Act: 11.4431. Min Act: -0.1700
Data Index: 6922048 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19