Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.4238. Min Act: -0.1700
Data Index: 386456 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3925. Min Act: -0.1700
Data Index: 8452931 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2050. Min Act: -0.1700
Data Index: 8552380 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2363. Min Act: -0.1700
Data Index: 8517908 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1113. Min Act: -0.1700
Data Index: 426978 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1425. Min Act: -0.1700
Data Index: 6529129 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0800. Min Act: -0.1700
Data Index: 2062591 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0800. Min Act: -0.1700
Data Index: 5475758 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0488. Min Act: -0.1700
Data Index: 8630267 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0488. Min Act: -0.1700
Data Index: 8065121 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0488. Min Act: -0.1700
Data Index: 6278405 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0175. Min Act: -0.1700
Data Index: 7531553 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0175. Min Act: -0.1700
Data Index: 241999 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0175. Min Act: -0.1700
Data Index: 20940 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4238. Min Range: -5.4238
Max Act: 4.9863. Min Act: -0.1700
Data Index: 1248098 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4238. Min Range: -5.4238
Max Act: 4.9863. Min Act: -0.1700
Data Index: 1586761 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4238. Min Range: -5.4238
Max Act: 4.9550. Min Act: -0.1700
Data Index: 8632764 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4238. Min Range: -5.4238
Max Act: 4.9550. Min Act: -0.1700
Data Index: 101446 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4238. Min Range: -5.4238
Max Act: 4.9238. Min Act: -0.1700
Data Index: 6765748 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4238. Min Range: -5.4238
Max Act: 4.9238. Min Act: -0.1700
Data Index: 352955 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19