Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.5624. Min Act: -0.1700
Data Index: 734795 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.2499. Min Act: -0.1700
Data Index: 3516307 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.2499. Min Act: -0.1700
Data Index: 5654278 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.1561. Min Act: -0.1700
Data Index: 4454705 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.1561. Min Act: -0.1700
Data Index: 4860136 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.1561. Min Act: -0.1700
Data Index: 1859000 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0936. Min Act: -0.1700
Data Index: 4232671 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.1249. Min Act: -0.1700
Data Index: 1711544 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.1249. Min Act: -0.1700
Data Index: 7859928 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0936. Min Act: -0.1700
Data Index: 573975 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0936. Min Act: -0.1700
Data Index: 86026 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0936. Min Act: -0.1700
Data Index: 2819265 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0624. Min Act: -0.1700
Data Index: 8773894 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0624. Min Act: -0.1700
Data Index: 7463588 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0624. Min Act: -0.1700
Data Index: 4614002 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0624. Min Act: -0.1700
Data Index: 205794 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0624. Min Act: -0.1700
Data Index: 8370535 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0624. Min Act: -0.1700
Data Index: 3687928 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0936. Min Act: -0.1700
Data Index: 4224295 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5624. Min Range: -4.5624
Max Act: 4.0311. Min Act: -0.1700
Data Index: 5475005 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19