Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.6442. Min Act: -0.1700
Data Index: 2653935 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.5817. Min Act: -0.1700
Data Index: 3987296 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.5817. Min Act: -0.1700
Data Index: 7595405 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.5817. Min Act: -0.1700
Data Index: 6708901 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.5504. Min Act: -0.1700
Data Index: 4021061 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.4879. Min Act: -0.1700
Data Index: 2584330 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.4879. Min Act: -0.1700
Data Index: 1998057 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.4879. Min Act: -0.1700
Data Index: 2425584 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.4567. Min Act: -0.1700
Data Index: 7559040 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.4567. Min Act: -0.1700
Data Index: 4060452 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.4567. Min Act: -0.1700
Data Index: 5773535 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.4254. Min Act: -0.1700
Data Index: 8416543 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3629. Min Act: -0.1700
Data Index: 3330791 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3942. Min Act: -0.1700
Data Index: 6778311 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3942. Min Act: -0.1700
Data Index: 5025935 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3942. Min Act: -0.1700
Data Index: 8097000 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3942. Min Act: -0.1700
Data Index: 5647337 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3942. Min Act: -0.1700
Data Index: 5101003 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3942. Min Act: -0.1700
Data Index: 7611408 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6442. Min Range: -4.6442
Max Act: 4.3942. Min Act: -0.1700
Data Index: 5075621 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19