Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.7734. Min Act: -0.1700
Data Index: 387446 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.7109. Min Act: -0.1700
Data Index: 2579298 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.4609. Min Act: -0.1700
Data Index: 1506115 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.5234. Min Act: -0.1700
Data Index: 7692589 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.3984. Min Act: -0.1700
Data Index: 2162713 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.3359. Min Act: -0.1700
Data Index: 5575259 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.2734. Min Act: -0.1700
Data Index: 8602639 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.3359. Min Act: -0.1700
Data Index: 2173165 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.2734. Min Act: -0.1700
Data Index: 267635 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.2734. Min Act: -0.1700
Data Index: 5453524 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.2734. Min Act: -0.1700
Data Index: 2338877 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.2109. Min Act: -0.1700
Data Index: 7353383 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.1484. Min Act: -0.1700
Data Index: 2918684 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.0859. Min Act: -0.1700
Data Index: 5180337 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.0859. Min Act: -0.1700
Data Index: 451203 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.0859. Min Act: -0.1700
Data Index: 2657931 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.0859. Min Act: -0.1700
Data Index: 4075877 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.0859. Min Act: -0.1700
Data Index: 2444848 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.0234. Min Act: -0.1700
Data Index: 2449401 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7734. Min Range: -9.7734
Max Act: 9.0234. Min Act: -0.1700
Data Index: 5156442 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19