Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4292 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2399. Min Range: -8.2399
Max Act: 8.2399. Min Act: -0.1700
Data Index: 6160936 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2399. Min Range: -8.2399
Max Act: 8.1774. Min Act: -0.1700
Data Index: 530338 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2399. Min Range: -8.2399
Max Act: 8.1774. Min Act: -0.1700
Data Index: 180212 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2399. Min Range: -8.2399
Max Act: 8.1774. Min Act: -0.1700
Data Index: 5144845 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2399. Min Range: -8.2399
Max Act: 8.0524. Min Act: -0.1700
Data Index: 5446342 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2399. Min Range: -8.2399
Max Act: 8.0524. Min Act: -0.1700
Data Index: 5991041 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.9899. Min Act: -0.1700
Data Index: 335216 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.9586. Min Act: -0.1700
Data Index: 5184444 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.8649. Min Act: -0.1700
Data Index: 5819462 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.8961. Min Act: -0.1700
Data Index: 5498025 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.8649. Min Act: -0.1700
Data Index: 8293139 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.8649. Min Act: -0.1700
Data Index: 5572248 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.8649. Min Act: -0.1700
Data Index: 6340479 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.8024. Min Act: -0.1700
Data Index: 5869008 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.8024. Min Act: -0.1700
Data Index: 3087393 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.7711. Min Act: -0.1700
Data Index: 987728 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.7399. Min Act: -0.1700
Data Index: 7880459 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.7399. Min Act: -0.1700
Data Index: 5607302 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.6774. Min Act: -0.1700
Data Index: 5694716 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2399. Min Range: -8.2399
Max Act: 7.7086. Min Act: -0.1700
Data Index: 6927907 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19