Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 543 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.4278. Min Act: -0.1700
Data Index: 8447566 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.2716. Min Act: -0.1700
Data Index: 8651397 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.2403. Min Act: -0.1700
Data Index: 5556125 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.1778. Min Act: -0.1700
Data Index: 1302366 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.0216. Min Act: -0.1700
Data Index: 541505 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.0216. Min Act: -0.1700
Data Index: 716837 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.0216. Min Act: -0.1700
Data Index: 4175405 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9903. Min Act: -0.1700
Data Index: 861902 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9903. Min Act: -0.1700
Data Index: 5797290 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9903. Min Act: -0.1700
Data Index: 8533486 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9591. Min Act: -0.1700
Data Index: 7831417 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9278. Min Act: -0.1700
Data Index: 5393065 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9903. Min Act: -0.1700
Data Index: 2838369 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9278. Min Act: -0.1700
Data Index: 4543349 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8966. Min Act: -0.1700
Data Index: 5574364 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8966. Min Act: -0.1700
Data Index: 5122739 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8966. Min Act: -0.1700
Data Index: 565153 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 451652 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 5790300 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 8632309 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19