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

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

Neuron 2262 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0001

Data Index: 587692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0408. Min Act: -0.0001

Data Index: 757341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1056827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0454. Min Act: -0.0001

Data Index: 973760 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0376. Min Act: -0.0001

Data Index: 809663 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0372. Min Act: -0.0001

Data Index: 856590 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1328149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0358. Min Act: -0.0001

Data Index: 267334 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0350. Min Act: -0.0001

Data Index: 755673 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0316. Min Act: -0.0001

Data Index: 629509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0337. Min Act: -0.0001

Data Index: 685134 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1310782 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0350. Min Act: -0.0001

Data Index: 936907 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1655450 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1575704 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1199787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1466804 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0324. Min Act: -0.0001

Data Index: 539707 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1575232 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1435323 (Python Code)

Max Activating Token Index: 1023