Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.6894. Min Act: -0.1700
Data Index: 2091614 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.4706. Min Act: -0.1700
Data Index: 4936827 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.4706. Min Act: -0.1700
Data Index: 1410216 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.3769. Min Act: -0.1700
Data Index: 6316785 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.3769. Min Act: -0.1700
Data Index: 3994450 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.3456. Min Act: -0.1700
Data Index: 5712502 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.3456. Min Act: -0.1700
Data Index: 4861820 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2831. Min Act: -0.1700
Data Index: 5747190 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2519. Min Act: -0.1700
Data Index: 46695 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2519. Min Act: -0.1700
Data Index: 7160818 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2519. Min Act: -0.1700
Data Index: 2434512 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2519. Min Act: -0.1700
Data Index: 6243518 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2206. Min Act: -0.1700
Data Index: 307339 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2206. Min Act: -0.1700
Data Index: 8445987 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2206. Min Act: -0.1700
Data Index: 8205041 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2206. Min Act: -0.1700
Data Index: 2157628 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2519. Min Act: -0.1700
Data Index: 8418114 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.2206. Min Act: -0.1700
Data Index: 6098329 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.1893. Min Act: -0.1700
Data Index: 4126790 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6894. Min Range: -4.6894
Max Act: 4.1893. Min Act: -0.1700
Data Index: 6481255 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19