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

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

Neuron 1742 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.8616. Min Act: -0.0000

Data Index: 887671 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4936. Min Act: -0.0000

Data Index: 224655 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.5445. Min Act: -0.0000

Data Index: 130470 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.5240. Min Act: -0.0000

Data Index: 767970 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.5329. Min Act: -0.0000

Data Index: 166186 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1117949 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.5501. Min Act: -0.0000

Data Index: 270630 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4873. Min Act: -0.0000

Data Index: 225858 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.5104. Min Act: -0.0000

Data Index: 43357 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1105203 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4241. Min Act: -0.0000

Data Index: 213040 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1625443 (Python Code)

Max Activating Token Index: 342

Text #12

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4343. Min Act: -0.0000

Data Index: 155905 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1381211 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1334643 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4284. Min Act: -0.0000

Data Index: 320816 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1281094 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.4336. Min Act: -0.0000

Data Index: 736512 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.3792. Min Act: -0.0000

Data Index: 245077 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1080926 (C4 (Web Text))

Max Activating Token Index: 281