Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3801 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.4756. Min Act: -0.1700
Data Index: 8633860 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.4131. Min Act: -0.1700
Data Index: 8106182 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.3506. Min Act: -0.1700
Data Index: 6427209 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.2568. Min Act: -0.1700
Data Index: 6376519 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.2256. Min Act: -0.1700
Data Index: 6007876 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.1943. Min Act: -0.1700
Data Index: 4221481 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.1631. Min Act: -0.1700
Data Index: 3526448 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.1631. Min Act: -0.1700
Data Index: 1491263 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.1006. Min Act: -0.1700
Data Index: 7118793 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.1006. Min Act: -0.1700
Data Index: 891787 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.0381. Min Act: -0.1700
Data Index: 377750 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4756. Min Range: -6.4756
Max Act: 6.1006. Min Act: -0.1700
Data Index: 7072198 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9443. Min Act: -0.1700
Data Index: 6269860 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9756. Min Act: -0.1700
Data Index: 3560787 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9756. Min Act: -0.1700
Data Index: 835303 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9443. Min Act: -0.1700
Data Index: 1282255 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9443. Min Act: -0.1700
Data Index: 1133821 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9443. Min Act: -0.1700
Data Index: 940643 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9443. Min Act: -0.1700
Data Index: 6840676 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4756. Min Range: -6.4756
Max Act: 5.9131. Min Act: -0.1700
Data Index: 7247678 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19