Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.9236. Min Act: -0.1700
Data Index: 4430608 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.5799. Min Act: -0.1700
Data Index: 5002339 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.4861. Min Act: -0.1700
Data Index: 4616932 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.3611. Min Act: -0.1700
Data Index: 7904618 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.3299. Min Act: -0.1700
Data Index: 4043063 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2986. Min Act: -0.1700
Data Index: 6091502 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2986. Min Act: -0.1700
Data Index: 7413265 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2986. Min Act: -0.1700
Data Index: 1349691 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2674. Min Act: -0.1700
Data Index: 370810 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2674. Min Act: -0.1700
Data Index: 3958726 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2361. Min Act: -0.1700
Data Index: 3440500 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2361. Min Act: -0.1700
Data Index: 3104784 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2049. Min Act: -0.1700
Data Index: 4887446 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.1736. Min Act: -0.1700
Data Index: 6912226 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2049. Min Act: -0.1700
Data Index: 7795940 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2049. Min Act: -0.1700
Data Index: 6987161 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.1736. Min Act: -0.1700
Data Index: 3984346 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.2049. Min Act: -0.1700
Data Index: 1247620 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.1736. Min Act: -0.1700
Data Index: 2029041 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9236. Min Range: -6.9236
Max Act: 6.1736. Min Act: -0.1700
Data Index: 7819268 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19