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

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

Neuron 168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0837. Min Act: -0.0001

Data Index: 420117 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0714. Min Act: -0.0001

Data Index: 338336 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0541. Min Act: -0.0000

Data Index: 79446 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1078062 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0569. Min Act: -0.0000

Data Index: 342339 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1220617 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1467056 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0730. Min Act: -0.0000

Data Index: 703337 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0578. Min Act: -0.0000

Data Index: 164659 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0624. Min Act: -0.0001

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0571. Min Act: -0.0001

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0544. Min Act: -0.0000

Data Index: 62058 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1321751 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0422. Min Act: -0.0000

Data Index: 793904 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1463261 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0515. Min Act: -0.0001

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1501648 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1521762 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0470. Min Act: -0.0000

Data Index: 967625 (C4 (Web Text))

Max Activating Token Index: 802