Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.8040. Min Act: -0.1700
Data Index: 3948437 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.6165. Min Act: -0.1700
Data Index: 3961744 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.6165. Min Act: -0.1700
Data Index: 5440943 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4915. Min Act: -0.1700
Data Index: 527804 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.5227. Min Act: -0.1700
Data Index: 5961344 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4915. Min Act: -0.1700
Data Index: 4662995 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.5540. Min Act: -0.1700
Data Index: 361397 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.5227. Min Act: -0.1700
Data Index: 8100494 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4602. Min Act: -0.1700
Data Index: 133829 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4602. Min Act: -0.1700
Data Index: 8649013 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4602. Min Act: -0.1700
Data Index: 7578921 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4602. Min Act: -0.1700
Data Index: 4015586 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4290. Min Act: -0.1700
Data Index: 8120383 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4290. Min Act: -0.1700
Data Index: 7702594 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4290. Min Act: -0.1700
Data Index: 5901217 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4290. Min Act: -0.1700
Data Index: 2291158 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.4290. Min Act: -0.1700
Data Index: 3153975 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.3977. Min Act: -0.1700
Data Index: 1288208 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.3665. Min Act: -0.1700
Data Index: 514136 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8040. Min Range: -4.8040
Max Act: 4.3977. Min Act: -0.1700
Data Index: 7668873 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19