Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2001 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1882. Min Range: -7.1882
Max Act: 7.1882. Min Act: -0.1700
Data Index: 1747741 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1882. Min Range: -7.1882
Max Act: 7.1257. Min Act: -0.1700
Data Index: 5557292 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.8444. Min Act: -0.1700
Data Index: 945644 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.8132. Min Act: -0.1700
Data Index: 8031935 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.8132. Min Act: -0.1700
Data Index: 1156261 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.8444. Min Act: -0.1700
Data Index: 2859850 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.8132. Min Act: -0.1700
Data Index: 7236916 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.8444. Min Act: -0.1700
Data Index: 1327155 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7819. Min Act: -0.1700
Data Index: 3501564 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7819. Min Act: -0.1700
Data Index: 7746060 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7819. Min Act: -0.1700
Data Index: 8479635 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7819. Min Act: -0.1700
Data Index: 6485305 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7507. Min Act: -0.1700
Data Index: 2362779 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7819. Min Act: -0.1700
Data Index: 5416991 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7507. Min Act: -0.1700
Data Index: 3915385 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7194. Min Act: -0.1700
Data Index: 3275266 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7194. Min Act: -0.1700
Data Index: 4683204 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7507. Min Act: -0.1700
Data Index: 7222471 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.6882. Min Act: -0.1700
Data Index: 3979893 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1882. Min Range: -7.1882
Max Act: 6.7194. Min Act: -0.1700
Data Index: 3253300 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19