Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 255 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.8246. Min Act: -0.1700
Data Index: 1794202 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.7934. Min Act: -0.1700
Data Index: 749656 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.7934. Min Act: -0.1700
Data Index: 490744 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.6996. Min Act: -0.1700
Data Index: 781422 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.6371. Min Act: -0.1700
Data Index: 5938451 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.6059. Min Act: -0.1700
Data Index: 504985 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.4809. Min Act: -0.1700
Data Index: 7552224 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.5121. Min Act: -0.1700
Data Index: 7637098 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.4496. Min Act: -0.1700
Data Index: 5458137 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.3871. Min Act: -0.1700
Data Index: 8707189 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.3246. Min Act: -0.1700
Data Index: 6893769 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.3871. Min Act: -0.1700
Data Index: 305440 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.2621. Min Act: -0.1700
Data Index: 1420571 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.2309. Min Act: -0.1700
Data Index: 2052245 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.1684. Min Act: -0.1700
Data Index: 5650500 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.1996. Min Act: -0.1700
Data Index: 6651746 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.1996. Min Act: -0.1700
Data Index: 7134255 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.1371. Min Act: -0.1700
Data Index: 7168046 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.2621. Min Act: -0.1700
Data Index: 31692 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8246. Min Range: -6.8246
Max Act: 6.1059. Min Act: -0.1700
Data Index: 6260052 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19