Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 81 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.5071. Min Act: -0.1700
Data Index: 4256672 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.4133. Min Act: -0.1700
Data Index: 4416028 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.2258. Min Act: -0.1700
Data Index: 8410973 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.2258. Min Act: -0.1700
Data Index: 8192346 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1946. Min Act: -0.1700
Data Index: 6173234 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1946. Min Act: -0.1700
Data Index: 8737292 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1946. Min Act: -0.1700
Data Index: 8590765 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1946. Min Act: -0.1700
Data Index: 5388301 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1946. Min Act: -0.1700
Data Index: 6741508 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1633. Min Act: -0.1700
Data Index: 3009224 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1633. Min Act: -0.1700
Data Index: 3135191 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1633. Min Act: -0.1700
Data Index: 5925927 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1633. Min Act: -0.1700
Data Index: 8587822 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1321. Min Act: -0.1700
Data Index: 7690201 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1321. Min Act: -0.1700
Data Index: 6914654 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1321. Min Act: -0.1700
Data Index: 448822 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1321. Min Act: -0.1700
Data Index: 6214940 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1321. Min Act: -0.1700
Data Index: 7705311 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1008. Min Act: -0.1700
Data Index: 4494854 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5071. Min Range: -5.5071
Max Act: 5.1008. Min Act: -0.1700
Data Index: 6111054 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19