Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5934 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.9491. Min Act: -0.1700
Data Index: 7849947 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8866. Min Act: -0.1700
Data Index: 2336848 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8241. Min Act: -0.1700
Data Index: 8437519 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8241. Min Act: -0.1700
Data Index: 7077507 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8241. Min Act: -0.1700
Data Index: 2156767 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8241. Min Act: -0.1700
Data Index: 3802894 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8241. Min Act: -0.1700
Data Index: 3859960 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8241. Min Act: -0.1700
Data Index: 8409709 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.8241. Min Act: -0.1700
Data Index: 7949117 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.7616. Min Act: -0.1700
Data Index: 811354 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.7616. Min Act: -0.1700
Data Index: 4451991 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 3932837 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 8789124 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 6191536 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 8365513 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.7616. Min Act: -0.1700
Data Index: 4278306 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 493894 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 6723176 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 3791148 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9491. Min Range: -7.9491
Max Act: 7.6991. Min Act: -0.1700
Data Index: 4439842 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19