Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.6890. Min Act: -0.1700
Data Index: 4549277 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.5953. Min Act: -0.1700
Data Index: 7950743 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.5640. Min Act: -0.1700
Data Index: 7507962 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.5328. Min Act: -0.1700
Data Index: 7577561 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.4703. Min Act: -0.1700
Data Index: 5747940 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.4390. Min Act: -0.1700
Data Index: 7855083 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.4078. Min Act: -0.1700
Data Index: 1745978 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.3765. Min Act: -0.1700
Data Index: 7083868 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.3453. Min Act: -0.1700
Data Index: 2441784 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.3453. Min Act: -0.1700
Data Index: 6343225 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.3140. Min Act: -0.1700
Data Index: 5787228 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.3140. Min Act: -0.1700
Data Index: 8642025 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.3140. Min Act: -0.1700
Data Index: 6193096 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.2828. Min Act: -0.1700
Data Index: 3806610 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.2515. Min Act: -0.1700
Data Index: 1770074 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.2515. Min Act: -0.1700
Data Index: 6239481 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.2515. Min Act: -0.1700
Data Index: 6529478 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.2203. Min Act: -0.1700
Data Index: 345620 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.2515. Min Act: -0.1700
Data Index: 3685392 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6890. Min Range: -7.6890
Max Act: 7.2203. Min Act: -0.1700
Data Index: 2179044 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19