Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1490. Min Range: -8.1490
Max Act: 8.1490. Min Act: -0.1700
Data Index: 5131058 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.8990. Min Act: -0.1700
Data Index: 6794210 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.6803. Min Act: -0.1700
Data Index: 5977032 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.6490. Min Act: -0.1700
Data Index: 6011944 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.4928. Min Act: -0.1700
Data Index: 3435085 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.2740. Min Act: -0.1700
Data Index: 6169099 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.1490. Min Act: -0.1700
Data Index: 1230317 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.1490. Min Act: -0.1700
Data Index: 6420982 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.1178. Min Act: -0.1700
Data Index: 3402241 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.1490. Min Act: -0.1700
Data Index: 1960915 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.1803. Min Act: -0.1700
Data Index: 7235041 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.1178. Min Act: -0.1700
Data Index: 1480253 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.0553. Min Act: -0.1700
Data Index: 4276669 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.0553. Min Act: -0.1700
Data Index: 3163965 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1490. Min Range: -8.1490
Max Act: 7.0240. Min Act: -0.1700
Data Index: 262519 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1490. Min Range: -8.1490
Max Act: 6.8990. Min Act: -0.1700
Data Index: 3978528 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1490. Min Range: -8.1490
Max Act: 6.9303. Min Act: -0.1700
Data Index: 1365058 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1490. Min Range: -8.1490
Max Act: 6.9303. Min Act: -0.1700
Data Index: 2333241 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1490. Min Range: -8.1490
Max Act: 6.8678. Min Act: -0.1700
Data Index: 2987097 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1490. Min Range: -8.1490
Max Act: 6.8678. Min Act: -0.1700
Data Index: 4863855 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19