Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2825. Min Range: -8.2825
Max Act: 8.2825. Min Act: -0.1700
Data Index: 7815972 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.9700. Min Act: -0.1700
Data Index: 7399628 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.9700. Min Act: -0.1700
Data Index: 7815967 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.9075. Min Act: -0.1700
Data Index: 5001975 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.9075. Min Act: -0.1700
Data Index: 59160 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.9075. Min Act: -0.1700
Data Index: 5506519 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.9700. Min Act: -0.1700
Data Index: 728591 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.9075. Min Act: -0.1700
Data Index: 1186685 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.8450. Min Act: -0.1700
Data Index: 7815966 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.8138. Min Act: -0.1700
Data Index: 7815955 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.8450. Min Act: -0.1700
Data Index: 7815968 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.7513. Min Act: -0.1700
Data Index: 7815961 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.7513. Min Act: -0.1700
Data Index: 7815962 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.7200. Min Act: -0.1700
Data Index: 4858814 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.7513. Min Act: -0.1700
Data Index: 7815957 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.6888. Min Act: -0.1700
Data Index: 2257950 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.6888. Min Act: -0.1700
Data Index: 8597904 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.6888. Min Act: -0.1700
Data Index: 5001977 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.6575. Min Act: -0.1700
Data Index: 5675162 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2825. Min Range: -8.2825
Max Act: 7.6575. Min Act: -0.1700
Data Index: 189888 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19