Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1298 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0826. Min Range: -3.0826
Max Act: 3.0826. Min Act: -0.1700
Data Index: 3973848 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.9721. Min Act: -0.1700
Data Index: 3752504 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.9721. Min Act: -0.1700
Data Index: 2575757 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.9563. Min Act: -0.1700
Data Index: 2330224 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.9404. Min Act: -0.1700
Data Index: 3198415 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.9088. Min Act: -0.1700
Data Index: 158936 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.9088. Min Act: -0.1700
Data Index: 5299938 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8770. Min Act: -0.1700
Data Index: 1650109 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1949091 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8770. Min Act: -0.1700
Data Index: 8515193 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8612. Min Act: -0.1700
Data Index: 6860447 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8453. Min Act: -0.1700
Data Index: 2540748 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8453. Min Act: -0.1700
Data Index: 213424 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8453. Min Act: -0.1700
Data Index: 4379959 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8453. Min Act: -0.1700
Data Index: 6811844 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8294. Min Act: -0.1700
Data Index: 5442328 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8294. Min Act: -0.1700
Data Index: 3246513 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8294. Min Act: -0.1700
Data Index: 4669606 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8294. Min Act: -0.1700
Data Index: 3073337 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0826. Min Range: -3.0826
Max Act: 2.8135. Min Act: -0.1700
Data Index: 321999 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19