Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4165 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1011463 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1697. Min Act: -0.0000

Data Index: 919766 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1434. Min Act: -0.0000

Data Index: 124767 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1361. Min Act: -0.0000

Data Index: 779371 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1087813 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1324. Min Act: -0.0000

Data Index: 20040 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1306. Min Act: -0.0000

Data Index: 54020 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1325. Min Act: -0.0000

Data Index: 762119 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1426. Min Act: -0.0000

Data Index: 987930 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1234. Min Act: -0.0000

Data Index: 146769 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1233. Min Act: -0.0000

Data Index: 235630 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1123. Min Act: -0.0000

Data Index: 989252 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1354. Min Act: -0.0001

Data Index: 174855 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1335. Min Act: -0.0000

Data Index: 422132 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1220. Min Act: -0.0000

Data Index: 145159 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1169. Min Act: -0.0001

Data Index: 275879 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1140. Min Act: -0.0001

Data Index: 90999 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1300065 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1170. Min Act: -0.0000

Data Index: 343596 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1297145 (C4 (Web Text))

Max Activating Token Index: 344