Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1568 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.4187. Min Act: -0.1700
Data Index: 3770473 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3560. Min Act: -0.1700
Data Index: 2710321 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3246. Min Act: -0.1700
Data Index: 6245677 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.2618. Min Act: -0.1700
Data Index: 555230 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.2304. Min Act: -0.1700
Data Index: 5193643 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.2304. Min Act: -0.1700
Data Index: 553201 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1989. Min Act: -0.1700
Data Index: 560318 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1989. Min Act: -0.1700
Data Index: 7723134 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1675. Min Act: -0.1700
Data Index: 4677708 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1360. Min Act: -0.1700
Data Index: 6006436 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1517. Min Act: -0.1700
Data Index: 721925 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1517. Min Act: -0.1700
Data Index: 4508485 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1360. Min Act: -0.1700
Data Index: 5507309 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1360. Min Act: -0.1700
Data Index: 8360895 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1360. Min Act: -0.1700
Data Index: 3996803 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1360. Min Act: -0.1700
Data Index: 4550106 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1045. Min Act: -0.1700
Data Index: 4359160 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1045. Min Act: -0.1700
Data Index: 4823412 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.1045. Min Act: -0.1700
Data Index: 8746213 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.0887. Min Act: -0.1700
Data Index: 1498725 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19