Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0387. Min Range: -5.0387
Max Act: 5.0387. Min Act: -0.1700
Data Index: 1789465 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0387. Min Range: -5.0387
Max Act: 5.0387. Min Act: -0.1700
Data Index: 6113036 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.9137. Min Act: -0.1700
Data Index: 6679240 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.8825. Min Act: -0.1700
Data Index: 6517155 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.7887. Min Act: -0.1700
Data Index: 588421 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.7887. Min Act: -0.1700
Data Index: 4788454 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.7575. Min Act: -0.1700
Data Index: 1118936 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.7262. Min Act: -0.1700
Data Index: 234814 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6950. Min Act: -0.1700
Data Index: 2442105 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6950. Min Act: -0.1700
Data Index: 5929940 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.7262. Min Act: -0.1700
Data Index: 7534634 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6950. Min Act: -0.1700
Data Index: 5156340 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.7262. Min Act: -0.1700
Data Index: 3186073 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6950. Min Act: -0.1700
Data Index: 7400481 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6637. Min Act: -0.1700
Data Index: 4837320 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6325. Min Act: -0.1700
Data Index: 2374498 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6637. Min Act: -0.1700
Data Index: 244172 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6325. Min Act: -0.1700
Data Index: 6708882 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6325. Min Act: -0.1700
Data Index: 7343851 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0387. Min Range: -5.0387
Max Act: 4.6637. Min Act: -0.1700
Data Index: 857868 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19