Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3310. Min Range: -4.3310
Max Act: 4.3310. Min Act: -0.1700
Data Index: 7827016 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3310. Min Range: -4.3310
Max Act: 4.1748. Min Act: -0.1700
Data Index: 4125866 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3310. Min Range: -4.3310
Max Act: 4.0497. Min Act: -0.1700
Data Index: 8378522 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.9872. Min Act: -0.1700
Data Index: 1589910 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.9559. Min Act: -0.1700
Data Index: 3507436 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.9247. Min Act: -0.1700
Data Index: 3582664 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.9247. Min Act: -0.1700
Data Index: 7379924 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.9247. Min Act: -0.1700
Data Index: 906841 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8934. Min Act: -0.1700
Data Index: 4635542 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.9247. Min Act: -0.1700
Data Index: 4148438 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8465. Min Act: -0.1700
Data Index: 449532 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8622. Min Act: -0.1700
Data Index: 516718 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8465. Min Act: -0.1700
Data Index: 933688 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8465. Min Act: -0.1700
Data Index: 5939227 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8622. Min Act: -0.1700
Data Index: 5638630 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8309. Min Act: -0.1700
Data Index: 7390006 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8152. Min Act: -0.1700
Data Index: 1810544 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8152. Min Act: -0.1700
Data Index: 4528625 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8152. Min Act: -0.1700
Data Index: 6962396 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3310. Min Range: -4.3310
Max Act: 3.8152. Min Act: -0.1700
Data Index: 2549210 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19