Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.5535. Min Act: -0.1700
Data Index: 191169 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.5535. Min Act: -0.1700
Data Index: 6128877 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4597. Min Act: -0.1700
Data Index: 2548411 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4597. Min Act: -0.1700
Data Index: 6190480 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4597. Min Act: -0.1700
Data Index: 2009137 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4285. Min Act: -0.1700
Data Index: 4402286 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4285. Min Act: -0.1700
Data Index: 2009853 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4285. Min Act: -0.1700
Data Index: 7663607 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4285. Min Act: -0.1700
Data Index: 30047 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.4285. Min Act: -0.1700
Data Index: 8303967 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3972. Min Act: -0.1700
Data Index: 5519228 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3972. Min Act: -0.1700
Data Index: 5349821 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3972. Min Act: -0.1700
Data Index: 2027875 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3972. Min Act: -0.1700
Data Index: 5078961 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3660. Min Act: -0.1700
Data Index: 402877 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3660. Min Act: -0.1700
Data Index: 183419 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3660. Min Act: -0.1700
Data Index: 4531351 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3660. Min Act: -0.1700
Data Index: 6524284 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3660. Min Act: -0.1700
Data Index: 6067776 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5535. Min Range: -5.5535
Max Act: 5.3347. Min Act: -0.1700
Data Index: 5632236 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19