Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2993 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.7215. Min Act: -0.0001
Data Index: 202266 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.8108. Min Act: -0.0001
Data Index: 836479 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.8159. Min Act: -0.0001
Data Index: 939214 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6608. Min Act: -0.0001
Data Index: 986340 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6576. Min Act: -0.0001
Data Index: 827247 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.7221. Min Act: -0.0001
Data Index: 675260 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6927. Min Act: -0.0001
Data Index: 1303560 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6842. Min Act: -0.0001
Data Index: 1181175 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6898. Min Act: -0.0001
Data Index: 10550 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.5504. Min Act: -0.0001
Data Index: 135620 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6706. Min Act: -0.0001
Data Index: 796594 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.5152. Min Act: -0.0001
Data Index: 27988 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.7806. Min Act: -0.0001
Data Index: 14324 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6746. Min Act: -0.0001
Data Index: 1272080 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.5847. Min Act: -0.0001
Data Index: 227922 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.4835. Min Act: -0.0001
Data Index: 456524 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.4942. Min Act: -0.0001
Data Index: 282934 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.6394. Min Act: -0.0001
Data Index: 232159 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.5460. Min Act: -0.0001
Data Index: 501256 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8159. Min Range: -1.8159
Max Act: 1.4691. Min Act: -0.0001
Data Index: 728473 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19