Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 897 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.8628. Min Act: -0.1700
Data Index: 7868723 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.7378. Min Act: -0.1700
Data Index: 5189474 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.7378. Min Act: -0.1700
Data Index: 7696875 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.7690. Min Act: -0.1700
Data Index: 300707 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6753. Min Act: -0.1700
Data Index: 5944672 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.7065. Min Act: -0.1700
Data Index: 3559689 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.7065. Min Act: -0.1700
Data Index: 8765139 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6753. Min Act: -0.1700
Data Index: 2102189 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6440. Min Act: -0.1700
Data Index: 5367309 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6753. Min Act: -0.1700
Data Index: 4196579 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6440. Min Act: -0.1700
Data Index: 8273896 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6440. Min Act: -0.1700
Data Index: 5376078 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6440. Min Act: -0.1700
Data Index: 5782048 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6440. Min Act: -0.1700
Data Index: 598124 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6440. Min Act: -0.1700
Data Index: 1528011 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6128. Min Act: -0.1700
Data Index: 371383 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6128. Min Act: -0.1700
Data Index: 3981571 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6128. Min Act: -0.1700
Data Index: 3259207 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6128. Min Act: -0.1700
Data Index: 4563383 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8628. Min Range: -4.8628
Max Act: 4.6440. Min Act: -0.1700
Data Index: 6134839 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19