Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.8567. Min Act: -0.1700
Data Index: 2523395 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.6692. Min Act: -0.1700
Data Index: 6787785 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.4817. Min Act: -0.1700
Data Index: 441367 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.4817. Min Act: -0.1700
Data Index: 3865755 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.4505. Min Act: -0.1700
Data Index: 5745874 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.3567. Min Act: -0.1700
Data Index: 4900583 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.3255. Min Act: -0.1700
Data Index: 5503772 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.3255. Min Act: -0.1700
Data Index: 3362215 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2942. Min Act: -0.1700
Data Index: 186893 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.4505. Min Act: -0.1700
Data Index: 4499898 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.3255. Min Act: -0.1700
Data Index: 3363640 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2942. Min Act: -0.1700
Data Index: 7348751 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2630. Min Act: -0.1700
Data Index: 1338000 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2942. Min Act: -0.1700
Data Index: 5555843 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2630. Min Act: -0.1700
Data Index: 4686784 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2005. Min Act: -0.1700
Data Index: 6569869 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.1692. Min Act: -0.1700
Data Index: 5439921 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2317. Min Act: -0.1700
Data Index: 4129044 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2005. Min Act: -0.1700
Data Index: 5555839 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8567. Min Range: -8.8567
Max Act: 8.2317. Min Act: -0.1700
Data Index: 2623486 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19