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

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

Neuron 2891 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2497. Min Range: -5.2497

Max Act: 5.2497. Min Act: -0.0000

Data Index: 936854 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.6960. Min Act: -0.0000

Data Index: 1056472 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.6021. Min Act: -0.0000

Data Index: 738364 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.6563. Min Act: -0.0000

Data Index: 1046286 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.3772. Min Act: -0.0000

Data Index: 787728 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.4607. Min Act: -0.0000

Data Index: 892524 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.2221. Min Act: -0.0000

Data Index: 65804 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.3642. Min Act: -0.0000

Data Index: 257400 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.1681. Min Act: -0.0001

Data Index: 512510 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.0651. Min Act: -0.0000

Data Index: 926792 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.3946. Min Act: -0.0000

Data Index: 1195920 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.1421. Min Act: -0.0000

Data Index: 1174431 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.1453. Min Act: -0.0001

Data Index: 44281 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.0046. Min Act: -0.0000

Data Index: 1088933 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 5.2497. Min Range: -5.2497

Max Act: 1.9973. Min Act: -0.0000

Data Index: 880283 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 5.2497. Min Range: -5.2497

Max Act: 1.9924. Min Act: -0.0000

Data Index: 1330531 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 5.2497. Min Range: -5.2497

Max Act: 1.9505. Min Act: -0.0000

Data Index: 1114318 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.0507. Min Act: -0.0001

Data Index: 599712 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 5.2497. Min Range: -5.2497

Max Act: 2.1200. Min Act: -0.0001

Data Index: 1211974 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 5.2497. Min Range: -5.2497

Max Act: 1.9121. Min Act: -0.0001

Data Index: 99460 (C4 (Web Text))

Max Activating Token Index: 124