Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4425 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.8126. Min Act: -0.1700
Data Index: 8507504 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.7501. Min Act: -0.1700
Data Index: 7745720 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.7189. Min Act: -0.1700
Data Index: 6930791 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.7189. Min Act: -0.1700
Data Index: 3362087 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.6564. Min Act: -0.1700
Data Index: 4088684 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.5939. Min Act: -0.1700
Data Index: 1367291 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.5626. Min Act: -0.1700
Data Index: 1109981 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.5939. Min Act: -0.1700
Data Index: 3624389 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.5314. Min Act: -0.1700
Data Index: 3707444 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.5314. Min Act: -0.1700
Data Index: 73098 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.5314. Min Act: -0.1700
Data Index: 5721876 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.5001. Min Act: -0.1700
Data Index: 2582982 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4689. Min Act: -0.1700
Data Index: 1463312 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4376. Min Act: -0.1700
Data Index: 3939163 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4689. Min Act: -0.1700
Data Index: 8191819 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4376. Min Act: -0.1700
Data Index: 633598 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4689. Min Act: -0.1700
Data Index: 4067448 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4064. Min Act: -0.1700
Data Index: 5660374 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4064. Min Act: -0.1700
Data Index: 5272400 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8126. Min Range: -7.8126
Max Act: 7.4064. Min Act: -0.1700
Data Index: 3708759 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19