Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3873 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.7051. Min Act: -0.1700
Data Index: 3763599 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.5488. Min Act: -0.1700
Data Index: 1736598 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.5488. Min Act: -0.1700
Data Index: 5559108 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.5488. Min Act: -0.1700
Data Index: 3307301 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.5488. Min Act: -0.1700
Data Index: 3764453 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.4863. Min Act: -0.1700
Data Index: 3675909 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.4863. Min Act: -0.1700
Data Index: 889293 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.3613. Min Act: -0.1700
Data Index: 810713 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.3301. Min Act: -0.1700
Data Index: 391482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.3301. Min Act: -0.1700
Data Index: 4881867 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.3301. Min Act: -0.1700
Data Index: 664672 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.2676. Min Act: -0.1700
Data Index: 1335406 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.2363. Min Act: -0.1700
Data Index: 6754487 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.2051. Min Act: -0.1700
Data Index: 753271 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.1426. Min Act: -0.1700
Data Index: 438892 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.1113. Min Act: -0.1700
Data Index: 2745076 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.1113. Min Act: -0.1700
Data Index: 5250549 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.0801. Min Act: -0.1700
Data Index: 3698450 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.1113. Min Act: -0.1700
Data Index: 3532356 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7051. Min Range: -6.7051
Max Act: 6.1113. Min Act: -0.1700
Data Index: 2575344 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19