Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4312. Min Range: -7.4312
Max Act: 7.4312. Min Act: -0.1700
Data Index: 4227834 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4312. Min Range: -7.4312
Max Act: 7.0874. Min Act: -0.1700
Data Index: 7277684 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.9937. Min Act: -0.1700
Data Index: 2111667 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4312. Min Range: -7.4312
Max Act: 7.0249. Min Act: -0.1700
Data Index: 4342232 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.8999. Min Act: -0.1700
Data Index: 2148967 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.8374. Min Act: -0.1700
Data Index: 4273209 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.7749. Min Act: -0.1700
Data Index: 2447527 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.7437. Min Act: -0.1700
Data Index: 3088854 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.7437. Min Act: -0.1700
Data Index: 3262649 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.7124. Min Act: -0.1700
Data Index: 3160527 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.6812. Min Act: -0.1700
Data Index: 7933954 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.7124. Min Act: -0.1700
Data Index: 2635931 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.7124. Min Act: -0.1700
Data Index: 2791192 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.6812. Min Act: -0.1700
Data Index: 1482763 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.6812. Min Act: -0.1700
Data Index: 4598164 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.5874. Min Act: -0.1700
Data Index: 2131905 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.5874. Min Act: -0.1700
Data Index: 3229312 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.5874. Min Act: -0.1700
Data Index: 6969667 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.5874. Min Act: -0.1700
Data Index: 549468 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4312. Min Range: -7.4312
Max Act: 6.5874. Min Act: -0.1699
Data Index: 4850245 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19