Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.3823. Min Act: -0.1700
Data Index: 5118552 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.3510. Min Act: -0.1700
Data Index: 3323262 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.2260. Min Act: -0.1700
Data Index: 5139535 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.1948. Min Act: -0.1700
Data Index: 6269394 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4248534 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.1323. Min Act: -0.1700
Data Index: 2123720 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.0698. Min Act: -0.1700
Data Index: 8495024 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.0698. Min Act: -0.1700
Data Index: 5171662 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.0698. Min Act: -0.1700
Data Index: 4378925 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.0385. Min Act: -0.1700
Data Index: 1273187 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.0385. Min Act: -0.1700
Data Index: 7773603 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.9760. Min Act: -0.1700
Data Index: 1157801 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.9448. Min Act: -0.1700
Data Index: 2818228 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8823. Min Act: -0.1700
Data Index: 6717554 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8823. Min Act: -0.1700
Data Index: 7969183 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8823. Min Act: -0.1700
Data Index: 4519399 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.9135. Min Act: -0.1700
Data Index: 1679930 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8510. Min Act: -0.1700
Data Index: 3592993 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8510. Min Act: -0.1700
Data Index: 7294076 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8198. Min Act: -0.1700
Data Index: 7291306 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19