Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.5417. Min Act: -0.1700
Data Index: 396692 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.5729. Min Act: -0.1700
Data Index: 442265 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.5104. Min Act: -0.1700
Data Index: 2419027 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.5104. Min Act: -0.1700
Data Index: 5669423 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.4479. Min Act: -0.1700
Data Index: 2227129 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3854. Min Act: -0.1700
Data Index: 2771487 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3542. Min Act: -0.1700
Data Index: 1950761 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3229. Min Act: -0.1700
Data Index: 8468801 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2604. Min Act: -0.1700
Data Index: 6913054 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2604. Min Act: -0.1700
Data Index: 462659 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2292. Min Act: -0.1700
Data Index: 7414528 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2604. Min Act: -0.1700
Data Index: 1244240 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.1979. Min Act: -0.1700
Data Index: 1860014 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2292. Min Act: -0.1700
Data Index: 8375030 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.1979. Min Act: -0.1700
Data Index: 4037954 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2292. Min Act: -0.1700
Data Index: 4210852 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2292. Min Act: -0.1700
Data Index: 2492764 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2292. Min Act: -0.1700
Data Index: 4215584 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.1979. Min Act: -0.1700
Data Index: 3823594 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.1979. Min Act: -0.1700
Data Index: 1575205 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19