Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0738. Min Range: -5.0738
Max Act: 5.0738. Min Act: -0.1700
Data Index: 657832 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0738. Min Range: -5.0738
Max Act: 5.0738. Min Act: -0.1700
Data Index: 5619728 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.9175. Min Act: -0.1700
Data Index: 3766392 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.9488. Min Act: -0.1700
Data Index: 3022107 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8863. Min Act: -0.1700
Data Index: 7450625 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8863. Min Act: -0.1700
Data Index: 2572637 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8550. Min Act: -0.1700
Data Index: 768388 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8863. Min Act: -0.1700
Data Index: 3335295 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8863. Min Act: -0.1700
Data Index: 5159002 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8550. Min Act: -0.1700
Data Index: 2706078 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8550. Min Act: -0.1700
Data Index: 3053631 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8238. Min Act: -0.1700
Data Index: 1681860 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.8238. Min Act: -0.1700
Data Index: 8159125 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.7925. Min Act: -0.1700
Data Index: 1407668 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.7925. Min Act: -0.1700
Data Index: 7450626 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.7925. Min Act: -0.1700
Data Index: 344696 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.7925. Min Act: -0.1700
Data Index: 5225332 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.7613. Min Act: -0.1700
Data Index: 1763932 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.7300. Min Act: -0.1700
Data Index: 6953303 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0738. Min Range: -5.0738
Max Act: 4.7925. Min Act: -0.1700
Data Index: 7089587 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19