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

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

Neuron 4698 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: 0.8392. Min Range: -0.8392

Max Act: 0.8392. Min Act: -0.0001

Data Index: 420117 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.8045. Min Act: -0.0001

Data Index: 1656201 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1229643 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7341. Min Act: -0.0001

Data Index: 739868 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1330680 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7074. Min Act: -0.0001

Data Index: 321860 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7472. Min Act: -0.0001

Data Index: 1638399 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1253758 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7186. Min Act: -0.0001

Data Index: 367400 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7187. Min Act: -0.0001

Data Index: 967395 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.6995. Min Act: -0.0001

Data Index: 934597 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7839. Min Act: -0.0001

Data Index: 286281 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7580. Min Act: -0.0001

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7306. Min Act: -0.0001

Data Index: 23793 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7236. Min Act: -0.0001

Data Index: 976190 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7543. Min Act: -0.0001

Data Index: 1045809 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.6937. Min Act: -0.0001

Data Index: 1165335 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7698. Min Act: -0.0001

Data Index: 99552 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7378. Min Act: -0.0001

Data Index: 596878 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.6837. Min Act: -0.0001

Data Index: 738278 (C4 (Web Text))

Max Activating Token Index: 34