Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.9955. Min Range: -17.9955
Max Act: 17.9955. Min Act: -0.1700
Data Index: 4648163 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.9955. Min Range: -17.9955
Max Act: 17.6205. Min Act: -0.1700
Data Index: 1250772 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.9955. Min Range: -17.9955
Max Act: 17.2455. Min Act: -0.1700
Data Index: 1164370 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.9955. Min Range: -17.9955
Max Act: 17.1205. Min Act: -0.1700
Data Index: 7085798 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.9955. Min Range: -17.9955
Max Act: 17.1205. Min Act: -0.1700
Data Index: 952751 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.9955. Min Act: -0.1700
Data Index: 3837214 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.8705. Min Act: -0.1700
Data Index: 3120472 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.7455. Min Act: -0.1700
Data Index: 240520 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.7455. Min Act: -0.1700
Data Index: 2383347 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.7455. Min Act: -0.1700
Data Index: 1871752 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.6205. Min Act: -0.1700
Data Index: 3616828 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.4955. Min Act: -0.1700
Data Index: 5491697 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.4955. Min Act: -0.1700
Data Index: 4651020 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.4955. Min Act: -0.1700
Data Index: 6705837 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.4955. Min Act: -0.1700
Data Index: 7694938 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.3705. Min Act: -0.1700
Data Index: 157158 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.3705. Min Act: -0.1700
Data Index: 6086150 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.3705. Min Act: -0.1700
Data Index: 1573705 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.3705. Min Act: -0.1700
Data Index: 6188206 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.9955. Min Range: -17.9955
Max Act: 16.3705. Min Act: -0.1700
Data Index: 2984891 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19