Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1323. Min Range: -6.1323
Max Act: 6.1323. Min Act: -0.1700
Data Index: 1585941 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1323. Min Range: -6.1323
Max Act: 6.1011. Min Act: -0.1700
Data Index: 856628 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6948. Min Act: -0.1700
Data Index: 4386290 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6636. Min Act: -0.1700
Data Index: 632369 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6636. Min Act: -0.1700
Data Index: 6455293 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6323. Min Act: -0.1700
Data Index: 1748408 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6011. Min Act: -0.1700
Data Index: 6455292 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6011. Min Act: -0.1700
Data Index: 1461480 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6011. Min Act: -0.1700
Data Index: 3831670 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5698. Min Act: -0.1700
Data Index: 1262409 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5386. Min Act: -0.1700
Data Index: 119007 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5386. Min Act: -0.1700
Data Index: 8485294 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5698. Min Act: -0.1700
Data Index: 7813138 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5073. Min Act: -0.1700
Data Index: 5603041 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4761. Min Act: -0.1700
Data Index: 8613119 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5073. Min Act: -0.1700
Data Index: 3096204 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4761. Min Act: -0.1700
Data Index: 5876249 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4761. Min Act: -0.1700
Data Index: 6073813 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4761. Min Act: -0.1700
Data Index: 1751066 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4761. Min Act: -0.1700
Data Index: 3583827 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19