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

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

Neuron 2561 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.7332. Min Act: -0.0000

Data Index: 1074834 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.0211. Min Act: -0.0000

Data Index: 485989 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.9012. Min Act: -0.0000

Data Index: 8668 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.7979. Min Act: -0.0000

Data Index: 1135583 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.7095. Min Act: -0.0000

Data Index: 524258 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.6903. Min Act: -0.0000

Data Index: 1052635 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.4983. Min Act: -0.0000

Data Index: 82721 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.6539. Min Act: -0.0000

Data Index: 878651 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1324985 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1249251 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.3833. Min Act: -0.0000

Data Index: 364200 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.3714. Min Act: -0.0000

Data Index: 18145 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.5180. Min Act: -0.0000

Data Index: 155971 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.4933. Min Act: -0.0000

Data Index: 944249 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.4870. Min Act: -0.0000

Data Index: 156600 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.3006. Min Act: -0.0000

Data Index: 309093 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.3748. Min Act: -0.0000

Data Index: 562951 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.4512. Min Act: -0.0000

Data Index: 439453 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.2987. Min Act: -0.0000

Data Index: 754049 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 2.7332. Min Range: -2.7332

Max Act: 1.4307. Min Act: -0.0000

Data Index: 450682 (C4 (Web Text))

Max Activating Token Index: 748