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

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

Neuron 3783 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: 1.2440. Min Range: -1.2440

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1280156 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.1623. Min Act: -0.0000

Data Index: 501104 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1355240 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.0418. Min Act: -0.0000

Data Index: 482132 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.1342. Min Act: -0.0000

Data Index: 537950 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.1299. Min Act: -0.0000

Data Index: 383561 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1127710 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.0013. Min Act: -0.0000

Data Index: 567336 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.0256. Min Act: -0.0000

Data Index: 566501 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1427985 (Python Code)

Max Activating Token Index: 562

Text #10

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1623549 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1103646 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.2440. Min Range: -1.2440

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1181440 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.9813. Min Act: -0.0000

Data Index: 406240 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.9402. Min Act: -0.0000

Data Index: 637948 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1253697 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.9307. Min Act: -0.0000

Data Index: 4878 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.9321. Min Act: -0.0000

Data Index: 534562 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1142639 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.2440. Min Range: -1.2440

Max Act: 0.8971. Min Act: -0.0000

Data Index: 523255 (C4 (Web Text))

Max Activating Token Index: 494