Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.6477. Min Act: -0.1700
Data Index: 4506383 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.5852. Min Act: -0.1700
Data Index: 6157231 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.5539. Min Act: -0.1700
Data Index: 4061061 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.5539. Min Act: -0.1700
Data Index: 1154317 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.5227. Min Act: -0.1700
Data Index: 2601511 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4914. Min Act: -0.1700
Data Index: 1522217 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4602. Min Act: -0.1700
Data Index: 6786978 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4602. Min Act: -0.1700
Data Index: 4873938 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4602. Min Act: -0.1700
Data Index: 5523517 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4289. Min Act: -0.1700
Data Index: 7096098 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4289. Min Act: -0.1700
Data Index: 4486627 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4289. Min Act: -0.1700
Data Index: 5555035 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4289. Min Act: -0.1700
Data Index: 2945988 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4289. Min Act: -0.1700
Data Index: 8147868 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.3977. Min Act: -0.1700
Data Index: 2011984 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.4602. Min Act: -0.1700
Data Index: 5906684 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.3977. Min Act: -0.1700
Data Index: 3369321 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.3664. Min Act: -0.1700
Data Index: 5579106 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.3977. Min Act: -0.1700
Data Index: 5358782 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6477. Min Range: -5.6477
Max Act: 5.3977. Min Act: -0.1700
Data Index: 2969773 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19