Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5203 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.7488. Min Act: -0.1700
Data Index: 7223988 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6014792 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.6551. Min Act: -0.1700
Data Index: 673761 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.5926. Min Act: -0.1700
Data Index: 6660878 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.5613. Min Act: -0.1700
Data Index: 803425 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4988. Min Act: -0.1700
Data Index: 169862 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4676. Min Act: -0.1700
Data Index: 6225832 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4363. Min Act: -0.1700
Data Index: 6592205 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4363. Min Act: -0.1700
Data Index: 7339828 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4676. Min Act: -0.1700
Data Index: 2404381 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4051. Min Act: -0.1700
Data Index: 1979600 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4051. Min Act: -0.1700
Data Index: 8716388 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 6831734 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 3364781 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3426. Min Act: -0.1700
Data Index: 4902994 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3426. Min Act: -0.1700
Data Index: 3952088 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3426. Min Act: -0.1700
Data Index: 6157806 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3426. Min Act: -0.1700
Data Index: 3848248 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3426. Min Act: -0.1700
Data Index: 5514864 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3426. Min Act: -0.1700
Data Index: 121250 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19