Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.6823. Min Act: -0.1700
Data Index: 8286482 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.6511. Min Act: -0.1700
Data Index: 3803148 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.5261. Min Act: -0.1700
Data Index: 7064423 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4948. Min Act: -0.1700
Data Index: 6045318 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4636. Min Act: -0.1700
Data Index: 2543238 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4948. Min Act: -0.1700
Data Index: 1521970 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4948. Min Act: -0.1700
Data Index: 1783696 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4948. Min Act: -0.1700
Data Index: 2770003 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4636. Min Act: -0.1700
Data Index: 6091963 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4323. Min Act: -0.1700
Data Index: 1058434 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4323. Min Act: -0.1700
Data Index: 1860103 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4323. Min Act: -0.1700
Data Index: 953616 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4011. Min Act: -0.1700
Data Index: 2400615 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4011. Min Act: -0.1700
Data Index: 4503425 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.4011. Min Act: -0.1700
Data Index: 2128889 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.3698. Min Act: -0.1700
Data Index: 3162962 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.3698. Min Act: -0.1700
Data Index: 2546228 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.3698. Min Act: -0.1700
Data Index: 3350324 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.3698. Min Act: -0.1700
Data Index: 3394467 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6823. Min Range: -5.6823
Max Act: 5.3386. Min Act: -0.1700
Data Index: 7565253 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19