Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5755 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.4084. Min Act: -0.1700
Data Index: 7665993 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.4084. Min Act: -0.1700
Data Index: 7551687 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.3772. Min Act: -0.1700
Data Index: 4210060 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.2834. Min Act: -0.1700
Data Index: 7702824 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.3147. Min Act: -0.1700
Data Index: 8016352 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.2522. Min Act: -0.1700
Data Index: 147497 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.2522. Min Act: -0.1700
Data Index: 847311 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.2209. Min Act: -0.1700
Data Index: 8581919 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1897. Min Act: -0.1700
Data Index: 5660774 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1897. Min Act: -0.1700
Data Index: 1829913 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1584. Min Act: -0.1700
Data Index: 8115332 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1584. Min Act: -0.1700
Data Index: 3643978 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1897. Min Act: -0.1700
Data Index: 3039065 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1584. Min Act: -0.1700
Data Index: 8050286 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.0959. Min Act: -0.1700
Data Index: 5894964 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1272. Min Act: -0.1700
Data Index: 4328445 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1272. Min Act: -0.1700
Data Index: 3542989 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.1272. Min Act: -0.1700
Data Index: 3716812 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.0959. Min Act: -0.1700
Data Index: 2297973 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4084. Min Range: -6.4084
Max Act: 6.0959. Min Act: -0.1700
Data Index: 5351848 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19