Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.6129. Min Act: -0.1700
Data Index: 75936 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.5817. Min Act: -0.1700
Data Index: 4894032 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.5192. Min Act: -0.1700
Data Index: 8343341 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.4254. Min Act: -0.1700
Data Index: 8343344 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3942. Min Act: -0.1700
Data Index: 2565484 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.4254. Min Act: -0.1700
Data Index: 2015356 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.4254. Min Act: -0.1700
Data Index: 8284572 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8768407 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3629. Min Act: -0.1700
Data Index: 4233682 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3629. Min Act: -0.1700
Data Index: 1984191 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3317. Min Act: -0.1700
Data Index: 2010761 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3317. Min Act: -0.1700
Data Index: 1191028 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3317. Min Act: -0.1700
Data Index: 1019458 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2692. Min Act: -0.1700
Data Index: 4809349 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2692. Min Act: -0.1700
Data Index: 1997369 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2692. Min Act: -0.1700
Data Index: 1301409 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2692. Min Act: -0.1700
Data Index: 3770021 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2379. Min Act: -0.1700
Data Index: 6177359 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2379. Min Act: -0.1700
Data Index: 5737183 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2379. Min Act: -0.1700
Data Index: 4901975 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19