Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1959. Min Act: -0.0000

Data Index: 98519 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1685. Min Act: -0.0000

Data Index: 862095 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1507. Min Act: -0.0000

Data Index: 90970 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1125389 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1457. Min Act: -0.0000

Data Index: 769723 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1372. Min Act: -0.0000

Data Index: 641915 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1458. Min Act: -0.0001

Data Index: 474791 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1243165 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1396. Min Act: -0.0000

Data Index: 726411 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1248001 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1377. Min Act: -0.0001

Data Index: 230625 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1283. Min Act: -0.0000

Data Index: 900614 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1328719 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1386. Min Act: -0.0000

Data Index: 137257 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1164921 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1268. Min Act: -0.0000

Data Index: 46037 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1308. Min Act: -0.0000

Data Index: 873953 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1269. Min Act: -0.0001

Data Index: 765779 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1342. Min Act: -0.0000

Data Index: 990908 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1240. Min Act: -0.0001

Data Index: 622199 (C4 (Web Text))

Max Activating Token Index: 405