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

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

Neuron 1510 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: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0000

Data Index: 959902 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0454. Min Act: -0.0000

Data Index: 101809 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0452. Min Act: -0.0000

Data Index: 822235 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0404. Min Act: -0.0000

Data Index: 215222 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0403. Min Act: -0.0000

Data Index: 686627 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1170073 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0369. Min Act: -0.0000

Data Index: 606770 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0362. Min Act: -0.0000

Data Index: 819283 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1197360 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0355. Min Act: -0.0000

Data Index: 45480 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0369. Min Act: -0.0000

Data Index: 316963 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0350. Min Act: -0.0000

Data Index: 890338 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1315759 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0335. Min Act: -0.0000

Data Index: 438717 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1581670 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0328. Min Act: -0.0000

Data Index: 1191929 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1620530 (Python Code)

Max Activating Token Index: 927

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0299. Min Act: -0.0000

Data Index: 357761 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0310. Min Act: -0.0000

Data Index: 974549 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1654484 (Python Code)

Max Activating Token Index: 998