Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.8823. Min Act: -0.1700
Data Index: 7686219 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.8198. Min Act: -0.1700
Data Index: 7583907 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.6635. Min Act: -0.1700
Data Index: 3840335 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.6323. Min Act: -0.1700
Data Index: 113610 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.6010. Min Act: -0.1700
Data Index: 4986114 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.5698. Min Act: -0.1700
Data Index: 7835831 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.5698. Min Act: -0.1700
Data Index: 3046426 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.5385. Min Act: -0.1700
Data Index: 5439920 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.5385. Min Act: -0.1700
Data Index: 2458264 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.5385. Min Act: -0.1700
Data Index: 8184009 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4760. Min Act: -0.1700
Data Index: 4728718 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4760. Min Act: -0.1700
Data Index: 8162935 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4760. Min Act: -0.1700
Data Index: 4513474 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4760. Min Act: -0.1700
Data Index: 3887507 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4760. Min Act: -0.1700
Data Index: 2432205 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4448. Min Act: -0.1700
Data Index: 4628958 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4448. Min Act: -0.1700
Data Index: 4089726 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4448. Min Act: -0.1700
Data Index: 5157050 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4448. Min Act: -0.1700
Data Index: 1416031 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8823. Min Range: -4.8823
Max Act: 4.4448. Min Act: -0.1700
Data Index: 7896074 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19