Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2288 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4363. Min Act: -0.1700
Data Index: 480423 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4051. Min Act: -0.1700
Data Index: 8012154 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4051. Min Act: -0.1700
Data Index: 8151280 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3738. Min Act: -0.1700
Data Index: 6078940 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 8762523 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 8082226 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2176. Min Act: -0.1700
Data Index: 4691546 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2176. Min Act: -0.1700
Data Index: 2853110 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 4462565 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 8066373 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 4333207 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 2332713 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1551. Min Act: -0.1700
Data Index: 1863947 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1551. Min Act: -0.1700
Data Index: 2508855 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1551. Min Act: -0.1700
Data Index: 4894401 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1238. Min Act: -0.1700
Data Index: 7599114 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0926. Min Act: -0.1700
Data Index: 136759 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0613. Min Act: -0.1700
Data Index: 4845511 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0613. Min Act: -0.1700
Data Index: 5104629 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0613. Min Act: -0.1700
Data Index: 7881816 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19