Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1403 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6127. Min Act: -0.0000

Data Index: 442629 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.7927. Min Act: -0.0001

Data Index: 1571596 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6793. Min Act: -0.0001

Data Index: 1533354 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6652. Min Act: -0.0001

Data Index: 358023 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6543. Min Act: -0.0001

Data Index: 958577 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6311. Min Act: -0.0001

Data Index: 929482 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6233. Min Act: -0.0001

Data Index: 661486 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.5272. Min Act: -0.0001

Data Index: 1610790 (Python Code)

Max Activating Token Index: 400

Text #8

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6161. Min Act: -0.0001

Data Index: 1563264 (Python Code)

Max Activating Token Index: 760

Text #9

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.5129. Min Act: -0.0001

Data Index: 452992 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.5879. Min Act: -0.0001

Data Index: 624301 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.5497. Min Act: -0.0001

Data Index: 1369964 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.4613. Min Act: -0.0001

Data Index: 1314940 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.5390. Min Act: -0.0001

Data Index: 253218 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6276. Min Act: -0.0001

Data Index: 287428 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.6356. Min Act: -0.0001

Data Index: 25988 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.5286. Min Act: -0.0001

Data Index: 171585 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.5423. Min Act: -0.0000

Data Index: 15849 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.3895. Min Act: -0.0001

Data Index: 1386589 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 1.7927. Min Range: -1.7927

Max Act: 1.4614. Min Act: -0.0001

Data Index: 223986 (C4 (Web Text))

Max Activating Token Index: 799