Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.3995. Min Act: -0.1700
Data Index: 1004655 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.2897. Min Act: -0.1700
Data Index: 2535633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.2897. Min Act: -0.1700
Data Index: 6867727 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.2740. Min Act: -0.1700
Data Index: 4122305 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.2111. Min Act: -0.1700
Data Index: 4291829 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.2269. Min Act: -0.1700
Data Index: 7473131 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1797. Min Act: -0.1700
Data Index: 4318454 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1640. Min Act: -0.1700
Data Index: 606220 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1640. Min Act: -0.1700
Data Index: 4315740 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1640. Min Act: -0.1700
Data Index: 696980 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1482. Min Act: -0.1700
Data Index: 1156025 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1167. Min Act: -0.1700
Data Index: 495050 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1167. Min Act: -0.1700
Data Index: 8481225 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1010. Min Act: -0.1700
Data Index: 3949072 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.1167. Min Act: -0.1700
Data Index: 6175291 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.0694. Min Act: -0.1700
Data Index: 4225448 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.0852. Min Act: -0.1700
Data Index: 1121491 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.0694. Min Act: -0.1700
Data Index: 7836860 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.0694. Min Act: -0.1700
Data Index: 4262152 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3995. Min Range: -3.3995
Max Act: 3.0537. Min Act: -0.1700
Data Index: 7241689 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19