Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1292 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.8953. Min Act: -0.1700
Data Index: 4396500 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.8640. Min Act: -0.1700
Data Index: 4483147 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.7390. Min Act: -0.1700
Data Index: 5546341 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.6453. Min Act: -0.1700
Data Index: 2444191 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.6453. Min Act: -0.1700
Data Index: 713314 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.6140. Min Act: -0.1700
Data Index: 4396498 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.4578. Min Act: -0.1700
Data Index: 3112102 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3953. Min Act: -0.1700
Data Index: 3417302 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3953. Min Act: -0.1700
Data Index: 3737526 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3953. Min Act: -0.1700
Data Index: 883210 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3953. Min Act: -0.1700
Data Index: 7030728 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3640. Min Act: -0.1700
Data Index: 6424546 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3640. Min Act: -0.1700
Data Index: 1994524 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3640. Min Act: -0.1700
Data Index: 8561234 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3640. Min Act: -0.1700
Data Index: 6424542 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3328. Min Act: -0.1700
Data Index: 6018655 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3015. Min Act: -0.1700
Data Index: 8519437 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3640. Min Act: -0.1700
Data Index: 4396502 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.3328. Min Act: -0.1700
Data Index: 3542264 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8953. Min Range: -7.8953
Max Act: 7.2703. Min Act: -0.1700
Data Index: 5003601 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19