Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.8453. Min Act: -0.1700
Data Index: 7908813 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.8141. Min Act: -0.1700
Data Index: 5170504 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.8453. Min Act: -0.1700
Data Index: 5156506 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.8141. Min Act: -0.1700
Data Index: 2661411 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.8141. Min Act: -0.1700
Data Index: 4897856 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.8141. Min Act: -0.1700
Data Index: 3655113 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7515. Min Act: -0.1700
Data Index: 58392 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 1127199 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 4862095 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 4742947 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7515. Min Act: -0.1700
Data Index: 4162636 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 935023 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 1950596 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 1837376 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 3505055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 3501613 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 3464441 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7515. Min Act: -0.1700
Data Index: 1307197 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 2661408 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8453. Min Range: -3.8453
Max Act: 3.7828. Min Act: -0.1700
Data Index: 1249941 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19