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

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

Neuron 4964 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1425. Min Range: -1.1425

Max Act: 1.1425. Min Act: -0.0000

Data Index: 296636 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1108448 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.1425. Min Range: -1.1425

Max Act: 1.1216. Min Act: -0.0000

Data Index: 147700 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.1425. Min Range: -1.1425

Max Act: 1.0541. Min Act: -0.0000

Data Index: 327853 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.9015. Min Act: -0.0000

Data Index: 867392 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1173575 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.8207. Min Act: -0.0000

Data Index: 17377 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1015308 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7377. Min Act: -0.0000

Data Index: 343964 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7337. Min Act: -0.0000

Data Index: 70473 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7209. Min Act: -0.0000

Data Index: 749288 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7115. Min Act: -0.0000

Data Index: 651526 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7888. Min Act: -0.0000

Data Index: 457419 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7569. Min Act: -0.0000

Data Index: 680367 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7247. Min Act: -0.0000

Data Index: 82023 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1255534 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1359021 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.7812. Min Act: -0.0000

Data Index: 181590 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.6056. Min Act: -0.0000

Data Index: 265972 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.1425. Min Range: -1.1425

Max Act: 0.6270. Min Act: -0.0000

Data Index: 464590 (C4 (Web Text))

Max Activating Token Index: 571