Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3688. Min Range: -7.3688
Max Act: 7.3688. Min Act: -0.1700
Data Index: 5736284 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3688. Min Range: -7.3688
Max Act: 7.0876. Min Act: -0.1700
Data Index: 6205381 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.9313. Min Act: -0.1700
Data Index: 5878351 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.8688. Min Act: -0.1700
Data Index: 8630858 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.8063. Min Act: -0.1700
Data Index: 2614896 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.8376. Min Act: -0.1700
Data Index: 5947000 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.8376. Min Act: -0.1700
Data Index: 4355741 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.7751. Min Act: -0.1700
Data Index: 6853824 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.7126. Min Act: -0.1700
Data Index: 5934627 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.6501. Min Act: -0.1700
Data Index: 5946999 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.5876. Min Act: -0.1700
Data Index: 1502960 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.5876. Min Act: -0.1700
Data Index: 1209400 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.5563. Min Act: -0.1700
Data Index: 5736288 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.5563. Min Act: -0.1700
Data Index: 2614895 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.5876. Min Act: -0.1700
Data Index: 7239033 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.4938. Min Act: -0.1700
Data Index: 2352490 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.4313. Min Act: -0.1700
Data Index: 2352491 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.4001. Min Act: -0.1700
Data Index: 7622380 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.2438. Min Act: -0.1700
Data Index: 6150466 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3688. Min Range: -7.3688
Max Act: 6.2126. Min Act: -0.1700
Data Index: 5883533 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19