Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4545 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5196. Min Range: -9.5196
Max Act: 9.5196. Min Act: -0.1700
Data Index: 2567813 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5196. Min Range: -9.5196
Max Act: 9.2071. Min Act: -0.1700
Data Index: 2770936 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5196. Min Range: -9.5196
Max Act: 9.1446. Min Act: -0.1700
Data Index: 6266101 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5196. Min Range: -9.5196
Max Act: 9.0821. Min Act: -0.1700
Data Index: 4209254 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.9571. Min Act: -0.1700
Data Index: 19380 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.7696. Min Act: -0.1700
Data Index: 7407205 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.7071. Min Act: -0.1700
Data Index: 6284672 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.7071. Min Act: -0.1700
Data Index: 3455608 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.6446. Min Act: -0.1700
Data Index: 1925722 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.6446. Min Act: -0.1700
Data Index: 5846317 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.6446. Min Act: -0.1700
Data Index: 1139865 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.6446. Min Act: -0.1700
Data Index: 8218699 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.6446. Min Act: -0.1700
Data Index: 88734 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.5821. Min Act: -0.1700
Data Index: 1253263 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.5821. Min Act: -0.1700
Data Index: 8306162 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.5821. Min Act: -0.1700
Data Index: 2026310 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.4571. Min Act: -0.1700
Data Index: 5681438 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.5196. Min Act: -0.1700
Data Index: 2523226 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.5196. Min Act: -0.1700
Data Index: 3143815 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5196. Min Range: -9.5196
Max Act: 8.4571. Min Act: -0.1700
Data Index: 4639230 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19