Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 85 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1194. Min Range: -5.1194
Max Act: 5.1194. Min Act: -0.1700
Data Index: 367431 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.8069. Min Act: -0.1700
Data Index: 2329359 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.7444. Min Act: -0.1700
Data Index: 263267 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.7132. Min Act: -0.1700
Data Index: 5373719 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.6507. Min Act: -0.1700
Data Index: 2238067 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.6194. Min Act: -0.1700
Data Index: 1475810 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5882. Min Act: -0.1700
Data Index: 3893170 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5882. Min Act: -0.1700
Data Index: 2541176 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5882. Min Act: -0.1700
Data Index: 287116 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5882. Min Act: -0.1700
Data Index: 559103 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5882. Min Act: -0.1700
Data Index: 7559021 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5882. Min Act: -0.1700
Data Index: 1689368 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5569. Min Act: -0.1700
Data Index: 5293742 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5257. Min Act: -0.1700
Data Index: 4414445 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5569. Min Act: -0.1700
Data Index: 6349330 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5257. Min Act: -0.1700
Data Index: 5068482 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.4944. Min Act: -0.1700
Data Index: 4754702 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.4944. Min Act: -0.1700
Data Index: 5348967 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.5257. Min Act: -0.1700
Data Index: 3358917 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1194. Min Range: -5.1194
Max Act: 4.4944. Min Act: -0.1700
Data Index: 930577 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19