Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5974. Min Act: -0.1700
Data Index: 1607446 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5974. Min Act: -0.1700
Data Index: 441790 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 256087 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5974. Min Act: -0.1700
Data Index: 257216 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5974. Min Act: -0.1700
Data Index: 5581568 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 5248744 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 7321840 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 6995962 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 1526378 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 6171099 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 6077688 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 916941 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 63783 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 1392047 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5348. Min Act: -0.1700
Data Index: 4896160 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 3630411 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 2469751 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5974. Min Act: -0.1700
Data Index: 766343 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 2017274 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5661. Min Act: -0.1700
Data Index: 1777377 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19