Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2027 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3852. Min Range: -4.3852

Max Act: 4.3852. Min Act: -0.0000

Data Index: 265287 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 4.3852. Min Range: -4.3852

Max Act: 4.0010. Min Act: -0.0000

Data Index: 1068571 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 4.3852. Min Range: -4.3852

Max Act: 4.1051. Min Act: -0.0000

Data Index: 168562 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 4.3852. Min Range: -4.3852

Max Act: 4.1040. Min Act: -0.0000

Data Index: 839698 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.1502. Min Act: -0.0000

Data Index: 340367 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 4.3852. Min Range: -4.3852

Max Act: 4.2685. Min Act: -0.0000

Data Index: 806010 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.4099. Min Act: -0.0000

Data Index: 854626 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 4.3852. Min Range: -4.3852

Max Act: 2.6752. Min Act: -0.0000

Data Index: 113536 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.2581. Min Act: -0.0000

Data Index: 4965 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 4.3852. Min Range: -4.3852

Max Act: 2.9035. Min Act: -0.0000

Data Index: 934436 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.6472. Min Act: -0.0000

Data Index: 102053 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.2735. Min Act: -0.0000

Data Index: 599936 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.2192. Min Act: -0.0000

Data Index: 460767 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 4.3852. Min Range: -4.3852

Max Act: 2.9623. Min Act: -0.0000

Data Index: 968603 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.2212. Min Act: -0.0000

Data Index: 473489 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.1082. Min Act: -0.0000

Data Index: 272579 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 4.3852. Min Range: -4.3852

Max Act: 3.0792. Min Act: -0.0000

Data Index: 1039838 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 4.3852. Min Range: -4.3852

Max Act: 2.9631. Min Act: -0.0000

Data Index: 1325230 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 4.3852. Min Range: -4.3852

Max Act: 2.9350. Min Act: -0.0000

Data Index: 274332 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 4.3852. Min Range: -4.3852

Max Act: 2.5295. Min Act: -0.0000

Data Index: 34884 (C4 (Web Text))

Max Activating Token Index: 888