Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 190 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.3248. Min Act: -0.1700
Data Index: 6273084 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.2623. Min Act: -0.1700
Data Index: 7311615 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.2623. Min Act: -0.1700
Data Index: 446200 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.1685. Min Act: -0.1700
Data Index: 8441891 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.1373. Min Act: -0.1700
Data Index: 8208735 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.1060. Min Act: -0.1700
Data Index: 4179888 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.1373. Min Act: -0.1700
Data Index: 81199 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.1373. Min Act: -0.1700
Data Index: 246934 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.1060. Min Act: -0.1700
Data Index: 8223655 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0435. Min Act: -0.1700
Data Index: 4296442 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0123. Min Act: -0.1700
Data Index: 4288651 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0123. Min Act: -0.1700
Data Index: 4052032 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0748. Min Act: -0.1700
Data Index: 7335182 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0123. Min Act: -0.1700
Data Index: 8007833 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0123. Min Act: -0.1700
Data Index: 6564202 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0435. Min Act: -0.1700
Data Index: 1764111 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3248. Min Range: -7.3248
Max Act: 6.9810. Min Act: -0.1700
Data Index: 6382086 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3248. Min Range: -7.3248
Max Act: 6.9498. Min Act: -0.1700
Data Index: 1002809 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3248. Min Range: -7.3248
Max Act: 7.0123. Min Act: -0.1700
Data Index: 8832388 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3248. Min Range: -7.3248
Max Act: 6.9498. Min Act: -0.1700
Data Index: 470103 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19