Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 423 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.7166. Min Act: -0.1700
Data Index: 4954514 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.7010. Min Act: -0.1700
Data Index: 4954504 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.6227. Min Act: -0.1700
Data Index: 7174860 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.5445. Min Act: -0.1700
Data Index: 679130 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.5758. Min Act: -0.1700
Data Index: 3673140 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4975. Min Act: -0.1700
Data Index: 6563689 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4662. Min Act: -0.1700
Data Index: 2481172 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4505. Min Act: -0.1700
Data Index: 5406707 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4662. Min Act: -0.1700
Data Index: 898213 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4662. Min Act: -0.1700
Data Index: 1885623 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4505. Min Act: -0.1700
Data Index: 7482337 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4348. Min Act: -0.1700
Data Index: 4800806 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4192. Min Act: -0.1700
Data Index: 42256 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4192. Min Act: -0.1700
Data Index: 1680097 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4035. Min Act: -0.1700
Data Index: 5743297 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4035. Min Act: -0.1700
Data Index: 8778548 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4192. Min Act: -0.1700
Data Index: 4143638 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4035. Min Act: -0.1700
Data Index: 3440134 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.4035. Min Act: -0.1700
Data Index: 5893330 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7166. Min Range: -3.7166
Max Act: 3.3878. Min Act: -0.1700
Data Index: 1310790 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19