Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.9414. Min Act: -0.1700
Data Index: 7534819 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.5351. Min Act: -0.1700
Data Index: 5539626 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.5351. Min Act: -0.1700
Data Index: 7600578 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4726. Min Act: -0.1700
Data Index: 2123271 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4414. Min Act: -0.1700
Data Index: 6220666 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4414. Min Act: -0.1700
Data Index: 451446 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4101. Min Act: -0.1700
Data Index: 1880257 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4101. Min Act: -0.1700
Data Index: 5129299 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4414. Min Act: -0.1700
Data Index: 2661548 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4101. Min Act: -0.1700
Data Index: 3191897 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3789. Min Act: -0.1700
Data Index: 4695224 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3789. Min Act: -0.1700
Data Index: 704095 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3476. Min Act: -0.1700
Data Index: 6097194 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3164. Min Act: -0.1700
Data Index: 7137516 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3164. Min Act: -0.1700
Data Index: 6310731 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3164. Min Act: -0.1700
Data Index: 5600918 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.2851. Min Act: -0.1700
Data Index: 7090849 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.2851. Min Act: -0.1700
Data Index: 6268179 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.2851. Min Act: -0.1700
Data Index: 5964376 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.2226. Min Act: -0.1700
Data Index: 2799699 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19