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

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

Neuron 4473 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1256. Min Range: -1.1256

Max Act: 1.1256. Min Act: -0.0002

Data Index: 1370053 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.8608. Min Act: -0.0002

Data Index: 1528076 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.8209. Min Act: -0.0002

Data Index: 1528752 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.8154. Min Act: -0.0002

Data Index: 1402125 (Python Code)

Max Activating Token Index: 726

Text #4

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.8175. Min Act: -0.0002

Data Index: 1429919 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7617. Min Act: -0.0002

Data Index: 86124 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7485. Min Act: -0.0002

Data Index: 400989 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7622. Min Act: -0.0002

Data Index: 1370222 (Python Code)

Max Activating Token Index: 712

Text #8

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7241. Min Act: -0.0002

Data Index: 844150 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7040. Min Act: -0.0002

Data Index: 1057213 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7372. Min Act: -0.0002

Data Index: 763523 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7196. Min Act: -0.0002

Data Index: 226655 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6727. Min Act: -0.0002

Data Index: 239846 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6387. Min Act: -0.0002

Data Index: 1402419 (Python Code)

Max Activating Token Index: 406

Text #14

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6695. Min Act: -0.0002

Data Index: 1535509 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6647. Min Act: -0.0002

Data Index: 1345265 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6777. Min Act: -0.0002

Data Index: 1578048 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6540. Min Act: -0.0002

Data Index: 1400933 (Python Code)

Max Activating Token Index: 576

Text #18

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6322. Min Act: -0.0002

Data Index: 857001 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5879. Min Act: -0.0002

Data Index: 1403866 (Python Code)

Max Activating Token Index: 226