Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.9923. Min Act: -0.1700
Data Index: 699585 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.9610. Min Act: -0.1700
Data Index: 1082873 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.9298. Min Act: -0.1700
Data Index: 3708517 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.8985. Min Act: -0.1700
Data Index: 1661518 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.8985. Min Act: -0.1700
Data Index: 3739317 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.8673. Min Act: -0.1700
Data Index: 316142 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.8048. Min Act: -0.1700
Data Index: 7783465 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.8360. Min Act: -0.1700
Data Index: 5600904 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.8048. Min Act: -0.1700
Data Index: 2351299 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.8360. Min Act: -0.1700
Data Index: 7124301 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7735. Min Act: -0.1700
Data Index: 1962408 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7735. Min Act: -0.1700
Data Index: 6473608 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7423. Min Act: -0.1700
Data Index: 6872893 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7423. Min Act: -0.1700
Data Index: 6645810 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7423. Min Act: -0.1700
Data Index: 1097085 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7735. Min Act: -0.1700
Data Index: 6153630 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7423. Min Act: -0.1700
Data Index: 5526964 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.7423. Min Act: -0.1700
Data Index: 1501400 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.6485. Min Act: -0.1700
Data Index: 3754027 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9923. Min Range: -4.9923
Max Act: 4.6798. Min Act: -0.1700
Data Index: 3310105 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19