Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2763 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5895. Min Range: -7.5895
Max Act: 7.5895. Min Act: -0.1700
Data Index: 6763504 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5895. Min Range: -7.5895
Max Act: 7.5270. Min Act: -0.1700
Data Index: 4317553 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5895. Min Range: -7.5895
Max Act: 7.3708. Min Act: -0.1700
Data Index: 989267 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5895. Min Range: -7.5895
Max Act: 7.3083. Min Act: -0.1700
Data Index: 7860643 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5895. Min Range: -7.5895
Max Act: 7.2145. Min Act: -0.1700
Data Index: 966932 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5895. Min Range: -7.5895
Max Act: 7.1208. Min Act: -0.1700
Data Index: 3010294 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5895. Min Range: -7.5895
Max Act: 7.0583. Min Act: -0.1700
Data Index: 1501058 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9958. Min Act: -0.1700
Data Index: 570304 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9958. Min Act: -0.1700
Data Index: 7760120 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9958. Min Act: -0.1700
Data Index: 2406865 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9333. Min Act: -0.1700
Data Index: 4523755 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9645. Min Act: -0.1700
Data Index: 5608040 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9020. Min Act: -0.1700
Data Index: 693951 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9020. Min Act: -0.1700
Data Index: 8504687 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9645. Min Act: -0.1700
Data Index: 8538212 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.8395. Min Act: -0.1700
Data Index: 3925205 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.9020. Min Act: -0.1700
Data Index: 2910596 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.8395. Min Act: -0.1700
Data Index: 7078671 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.8395. Min Act: -0.1700
Data Index: 8069486 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5895. Min Range: -7.5895
Max Act: 6.8708. Min Act: -0.1700
Data Index: 4139262 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19