Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1176 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.4170. Min Act: -0.1700
Data Index: 1947409 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.3858. Min Act: -0.1700
Data Index: 7958796 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.3858. Min Act: -0.1700
Data Index: 4857309 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.3545. Min Act: -0.1700
Data Index: 7670632 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.3233. Min Act: -0.1700
Data Index: 6094468 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.3233. Min Act: -0.1700
Data Index: 8397181 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.3233. Min Act: -0.1700
Data Index: 6362767 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2295. Min Act: -0.1700
Data Index: 7260581 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2295. Min Act: -0.1700
Data Index: 7133851 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2607. Min Act: -0.1700
Data Index: 1579649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2920. Min Act: -0.1700
Data Index: 6225572 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2920. Min Act: -0.1700
Data Index: 3649433 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2607. Min Act: -0.1700
Data Index: 5705395 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2607. Min Act: -0.1700
Data Index: 2042265 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2607. Min Act: -0.1700
Data Index: 6061143 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2607. Min Act: -0.1700
Data Index: 195512 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2607. Min Act: -0.1700
Data Index: 5930411 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2920. Min Act: -0.1700
Data Index: 527503 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2607. Min Act: -0.1700
Data Index: 6909737 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4170. Min Range: -4.4170
Max Act: 4.2295. Min Act: -0.1700
Data Index: 7050220 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19