Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4061 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0452. Min Range: -8.0452
Max Act: 8.0452. Min Act: -0.1700
Data Index: 1270491 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0452. Min Range: -8.0452
Max Act: 8.0140. Min Act: -0.1700
Data Index: 3395792 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.8265. Min Act: -0.1700
Data Index: 4329865 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.8265. Min Act: -0.1700
Data Index: 2325514 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.8577. Min Act: -0.1700
Data Index: 8414095 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.7952. Min Act: -0.1700
Data Index: 4169437 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.7952. Min Act: -0.1700
Data Index: 4494183 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.7327. Min Act: -0.1700
Data Index: 2383184 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.7640. Min Act: -0.1700
Data Index: 287721 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.6702. Min Act: -0.1700
Data Index: 8169854 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.7327. Min Act: -0.1700
Data Index: 5997616 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.6390. Min Act: -0.1700
Data Index: 3069580 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.6390. Min Act: -0.1700
Data Index: 2504670 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.6390. Min Act: -0.1700
Data Index: 6248391 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.6390. Min Act: -0.1700
Data Index: 4997782 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.5765. Min Act: -0.1700
Data Index: 4080264 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.6077. Min Act: -0.1700
Data Index: 1076072 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.5765. Min Act: -0.1700
Data Index: 5502446 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.5452. Min Act: -0.1700
Data Index: 7525406 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0452. Min Range: -8.0452
Max Act: 7.5452. Min Act: -0.1700
Data Index: 2227978 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19