Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.3909. Min Act: -0.1700
Data Index: 5840547 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2339. Min Act: -0.1700
Data Index: 225003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2339. Min Act: -0.1700
Data Index: 586466 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2339. Min Act: -0.1700
Data Index: 646405 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1911404 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1429351 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2339. Min Act: -0.1700
Data Index: 7867790 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 2231406 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 4081671 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 677242 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 3435924 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 1897438 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 2713462 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 4059007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 2540328 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 4943315 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 2984219 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.2025. Min Act: -0.1700
Data Index: 3852973 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.1395. Min Act: -0.1700
Data Index: 2833034 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3909. Min Range: -3.3909
Max Act: 3.1395. Min Act: -0.1700
Data Index: 3329373 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19