Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.4599. Min Act: -0.1700
Data Index: 2443711 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.2411. Min Act: -0.1700
Data Index: 6195393 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.2099. Min Act: -0.1700
Data Index: 1521366 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.1786. Min Act: -0.1700
Data Index: 2851447 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.1474. Min Act: -0.1700
Data Index: 4740348 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.1161. Min Act: -0.1700
Data Index: 5000074 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0849. Min Act: -0.1700
Data Index: 7947358 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0849. Min Act: -0.1700
Data Index: 2006448 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0849. Min Act: -0.1700
Data Index: 6295677 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0849. Min Act: -0.1700
Data Index: 150305 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0849. Min Act: -0.1700
Data Index: 6592436 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0223. Min Act: -0.1700
Data Index: 7824927 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0223. Min Act: -0.1700
Data Index: 7271070 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0223. Min Act: -0.1700
Data Index: 3794198 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4599. Min Range: -4.4599
Max Act: 4.0223. Min Act: -0.1700
Data Index: 7686821 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4599. Min Range: -4.4599
Max Act: 3.9911. Min Act: -0.1700
Data Index: 2516759 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4599. Min Range: -4.4599
Max Act: 3.9911. Min Act: -0.1700
Data Index: 1482263 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4599. Min Range: -4.4599
Max Act: 3.9598. Min Act: -0.1700
Data Index: 4606848 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4599. Min Range: -4.4599
Max Act: 3.9598. Min Act: -0.1700
Data Index: 1034887 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4599. Min Range: -4.4599
Max Act: 3.9598. Min Act: -0.1700
Data Index: 7806539 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19