Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.5977. Min Act: -0.1700
Data Index: 652223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.5664. Min Act: -0.1699
Data Index: 6638948 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4411. Min Act: -0.1700
Data Index: 2347399 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4724. Min Act: -0.1700
Data Index: 4174826 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4098. Min Act: -0.1700
Data Index: 2281258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4098. Min Act: -0.1700
Data Index: 1490135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3784. Min Act: -0.1700
Data Index: 2117001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4098. Min Act: -0.1700
Data Index: 7252229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4098. Min Act: -0.1697
Data Index: 1489660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4098. Min Act: -0.1700
Data Index: 3496257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3784. Min Act: -0.1700
Data Index: 1893413 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.4098. Min Act: -0.1700
Data Index: 1551199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3470. Min Act: -0.1689
Data Index: 5918803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3784. Min Act: -0.1700
Data Index: 3996320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3784. Min Act: -0.1700
Data Index: 164406 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3784. Min Act: -0.1700
Data Index: 300037 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3784. Min Act: -0.1699
Data Index: 4037379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3470. Min Act: -0.1700
Data Index: 963479 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3470. Min Act: -0.1700
Data Index: 1140378 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5977. Min Range: -3.5977
Max Act: 3.3470. Min Act: -0.1700
Data Index: 1504912 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19