Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3413 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.9380. Min Act: -0.1700
Data Index: 6259448 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.9380. Min Act: -0.1700
Data Index: 709255 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.7505. Min Act: -0.1700
Data Index: 2244974 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.6880. Min Act: -0.1700
Data Index: 2065078 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.6880. Min Act: -0.1700
Data Index: 5645481 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.6255. Min Act: -0.1700
Data Index: 5873651 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.6255. Min Act: -0.1700
Data Index: 1662344 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.5630. Min Act: -0.1700
Data Index: 392393 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.5630. Min Act: -0.1700
Data Index: 602254 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.2505. Min Act: -0.1700
Data Index: 168726 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.2505. Min Act: -0.1700
Data Index: 563482 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.2505. Min Act: -0.1700
Data Index: 2540347 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.1880. Min Act: -0.1700
Data Index: 8685750 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.2505. Min Act: -0.1700
Data Index: 8457422 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.1255. Min Act: -0.1700
Data Index: 7953711 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.1880. Min Act: -0.1700
Data Index: 5961174 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.1880. Min Act: -0.1700
Data Index: 7952710 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.1255. Min Act: -0.1700
Data Index: 2304876 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.1255. Min Act: -0.1700
Data Index: 2020816 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9380. Min Range: -10.9380
Max Act: 10.1255. Min Act: -0.1700
Data Index: 4929487 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19