Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.8402. Min Act: -0.1700
Data Index: 90275 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.7152. Min Act: -0.1700
Data Index: 6682649 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6527. Min Act: -0.1700
Data Index: 6043471 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6839. Min Act: -0.1700
Data Index: 1995586 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6527. Min Act: -0.1700
Data Index: 2393745 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6214. Min Act: -0.1700
Data Index: 8370149 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5902. Min Act: -0.1700
Data Index: 4944932 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5902. Min Act: -0.1700
Data Index: 2801815 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6214. Min Act: -0.1700
Data Index: 600896 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5589. Min Act: -0.1700
Data Index: 554739 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 7402753 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 7088720 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 5345163 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 3510693 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.4964. Min Act: -0.1700
Data Index: 83542 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.4964. Min Act: -0.1700
Data Index: 4794075 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.4964. Min Act: -0.1700
Data Index: 7101737 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.4964. Min Act: -0.1700
Data Index: 6890501 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 7738202 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.4964. Min Act: -0.1700
Data Index: 2922466 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19