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

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

Neuron 800 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0602. Min Range: -1.0602

Max Act: 1.0602. Min Act: -0.0000

Data Index: 374519 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.0602. Min Range: -1.0602

Max Act: 1.0225. Min Act: -0.0000

Data Index: 665024 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1102353 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1240741 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8323. Min Act: -0.0000

Data Index: 231323 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8679. Min Act: -0.0000

Data Index: 839171 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8317. Min Act: -0.0000

Data Index: 597011 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1110075 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7532. Min Act: -0.0000

Data Index: 42377 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7582. Min Act: -0.0000

Data Index: 719560 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6220. Min Act: -0.0000

Data Index: 392569 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6796. Min Act: -0.0000

Data Index: 375050 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1352572 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6377. Min Act: -0.0000

Data Index: 859165 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6264. Min Act: -0.0000

Data Index: 49618 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6388. Min Act: -0.0000

Data Index: 372522 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1040960 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6584. Min Act: -0.0000

Data Index: 802097 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6187. Min Act: -0.0000

Data Index: 214951 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1286185 (C4 (Web Text))

Max Activating Token Index: 267