Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5195 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0692. Min Range: -5.0692
Max Act: 5.0692. Min Act: -0.1700
Data Index: 6450689 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.9442. Min Act: -0.1700
Data Index: 8775737 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.7879. Min Act: -0.1700
Data Index: 525172 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.7254. Min Act: -0.1700
Data Index: 2747509 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6942. Min Act: -0.1700
Data Index: 892270 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6942. Min Act: -0.1700
Data Index: 1129639 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6942. Min Act: -0.1700
Data Index: 2278203 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6629. Min Act: -0.1700
Data Index: 4879187 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6317. Min Act: -0.1700
Data Index: 4803336 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6004. Min Act: -0.1700
Data Index: 5827188 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6004. Min Act: -0.1700
Data Index: 160056 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6004. Min Act: -0.1700
Data Index: 1474572 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6004. Min Act: -0.1700
Data Index: 4852728 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6004. Min Act: -0.1700
Data Index: 6467132 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.6004. Min Act: -0.1700
Data Index: 8775738 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.5692. Min Act: -0.1700
Data Index: 5020555 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.5379. Min Act: -0.1700
Data Index: 3920375 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.5379. Min Act: -0.1700
Data Index: 5688160 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.5379. Min Act: -0.1700
Data Index: 4238221 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0692. Min Range: -5.0692
Max Act: 4.5379. Min Act: -0.1700
Data Index: 7526493 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19