Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.8861. Min Act: -0.1700
Data Index: 4219832 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.8861. Min Act: -0.1700
Data Index: 5592891 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.8236. Min Act: -0.1700
Data Index: 1937904 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.8236. Min Act: -0.1700
Data Index: 674741 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.7611. Min Act: -0.1700
Data Index: 436480 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.5736. Min Act: -0.1700
Data Index: 8613539 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.5736. Min Act: -0.1700
Data Index: 4248182 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.5111. Min Act: -0.1700
Data Index: 5119669 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.3549. Min Act: -0.1700
Data Index: 2609620 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.3549. Min Act: -0.1700
Data Index: 6923015 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.3549. Min Act: -0.1700
Data Index: 4823747 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.3236. Min Act: -0.1700
Data Index: 8233755 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.3236. Min Act: -0.1700
Data Index: 950050 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.2299. Min Act: -0.1700
Data Index: 6027862 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.2299. Min Act: -0.1700
Data Index: 2145300 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.1986. Min Act: -0.1700
Data Index: 8037731 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.1986. Min Act: -0.1700
Data Index: 2150124 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.2299. Min Act: -0.1700
Data Index: 2987054 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.1986. Min Act: -0.1700
Data Index: 6286704 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8861. Min Range: -7.8861
Max Act: 7.1986. Min Act: -0.1700
Data Index: 4077712 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19