Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.6977. Min Act: -0.1700
Data Index: 5655389 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.5725. Min Act: -0.1700
Data Index: 1012603 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.5099. Min Act: -0.1700
Data Index: 7769488 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.4472. Min Act: -0.1700
Data Index: 3241502 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.4158. Min Act: -0.1700
Data Index: 2796031 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.4002. Min Act: -0.1700
Data Index: 6323971 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3845. Min Act: -0.1700
Data Index: 8558034 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3688. Min Act: -0.1700
Data Index: 4937744 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3374. Min Act: -0.1700
Data Index: 5655391 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3217. Min Act: -0.1700
Data Index: 386626 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3060. Min Act: -0.1700
Data Index: 7203928 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3374. Min Act: -0.1700
Data Index: 4937747 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3060. Min Act: -0.1700
Data Index: 5655390 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3374. Min Act: -0.1700
Data Index: 651217 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3060. Min Act: -0.1700
Data Index: 1444846 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.3060. Min Act: -0.1700
Data Index: 28742 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.2746. Min Act: -0.1700
Data Index: 3183665 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.2746. Min Act: -0.1700
Data Index: 7023519 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.2746. Min Act: -0.1700
Data Index: 3387354 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6977. Min Range: -3.6977
Max Act: 3.2746. Min Act: -0.1700
Data Index: 5474006 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19