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

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

Neuron 3183 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3251. Min Range: -5.3251

Max Act: 5.3251. Min Act: -0.0000

Data Index: 1192812 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.1711. Min Act: -0.0000

Data Index: 1121737 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.7082. Min Act: -0.0000

Data Index: 1158307 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 5.3251. Min Range: -5.3251

Max Act: 4.2522. Min Act: -0.0000

Data Index: 654531 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.8539. Min Act: -0.0000

Data Index: 903892 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.4862. Min Act: -0.0000

Data Index: 133166 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.5824. Min Act: -0.0000

Data Index: 257038 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.2357. Min Act: -0.0000

Data Index: 1157924 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.6456. Min Act: -0.0000

Data Index: 185187 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.1464. Min Act: -0.0000

Data Index: 1251378 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.9679. Min Act: -0.0000

Data Index: 1620490 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.9071. Min Act: -0.0000

Data Index: 535590 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.8496. Min Act: -0.0000

Data Index: 451919 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 5.3251. Min Range: -5.3251

Max Act: 3.2712. Min Act: -0.0000

Data Index: 1194370 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.6600. Min Act: -0.0000

Data Index: 1253832 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.7748. Min Act: -0.0000

Data Index: 1132540 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.6163. Min Act: -0.0000

Data Index: 266864 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.7644. Min Act: 0.0001

Data Index: 1235404 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.7511. Min Act: -0.0000

Data Index: 355221 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 5.3251. Min Range: -5.3251

Max Act: 2.8254. Min Act: 0.0000

Data Index: 699429 (C4 (Web Text))

Max Activating Token Index: 12