Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.1267. Min Act: -0.1700
Data Index: 4133542 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.1267. Min Act: -0.1700
Data Index: 2193309 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0952. Min Act: -0.1700
Data Index: 4572585 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.1110. Min Act: -0.1700
Data Index: 614410 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0795. Min Act: -0.1700
Data Index: 7265322 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0479. Min Act: -0.1700
Data Index: 2754113 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0321. Min Act: -0.1700
Data Index: 4669823 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0479. Min Act: -0.1700
Data Index: 2441397 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0005. Min Act: -0.1700
Data Index: 4133540 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0005. Min Act: -0.1700
Data Index: 5146873 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0163. Min Act: -0.1700
Data Index: 144029 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0005. Min Act: -0.1700
Data Index: 2374025 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1267. Min Range: -3.1267
Max Act: 2.9847. Min Act: -0.1700
Data Index: 6964444 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1267. Min Range: -3.1267
Max Act: 2.9847. Min Act: -0.1700
Data Index: 2077819 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1267. Min Range: -3.1267
Max Act: 2.9847. Min Act: -0.1700
Data Index: 7713299 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0005. Min Act: -0.1700
Data Index: 8302916 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1267. Min Range: -3.1267
Max Act: 3.0005. Min Act: -0.1700
Data Index: 2213928 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1267. Min Range: -3.1267
Max Act: 2.9847. Min Act: -0.1700
Data Index: 2547825 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1267. Min Range: -3.1267
Max Act: 2.9847. Min Act: -0.1700
Data Index: 3418246 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1267. Min Range: -3.1267
Max Act: 2.9531. Min Act: -0.1700
Data Index: 1536414 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19