Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.8858. Min Act: -0.1700
Data Index: 3266091 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.8223. Min Act: -0.1700
Data Index: 2531256 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.8382. Min Act: -0.1700
Data Index: 1076238 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.8382. Min Act: -0.1700
Data Index: 3875031 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7904. Min Act: -0.1700
Data Index: 2568630 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.8063. Min Act: -0.1700
Data Index: 904144 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.8063. Min Act: -0.1700
Data Index: 316549 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7745. Min Act: -0.1700
Data Index: 941336 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7904. Min Act: -0.1700
Data Index: 6795600 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7904. Min Act: -0.1700
Data Index: 3025669 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7745. Min Act: -0.1700
Data Index: 2895484 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7745. Min Act: -0.1700
Data Index: 8324174 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7585. Min Act: -0.1700
Data Index: 5880903 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7426. Min Act: -0.1700
Data Index: 3335456 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7585. Min Act: -0.1700
Data Index: 7872831 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7745. Min Act: -0.1700
Data Index: 8544610 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7745. Min Act: -0.1700
Data Index: 745899 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7426. Min Act: -0.1700
Data Index: 4474780 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7585. Min Act: -0.1700
Data Index: 1360401 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8858. Min Range: -2.8858
Max Act: 2.7585. Min Act: -0.1700
Data Index: 200654 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19