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

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

Neuron 2534 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: 0.0599. Min Range: -0.0599

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1286453 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0002

Data Index: 508298 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1357456 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1122091 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0533. Min Act: -0.0002

Data Index: 714814 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0519. Min Act: -0.0002

Data Index: 478825 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0486. Min Act: -0.0002

Data Index: 248732 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1075665 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0460. Min Act: -0.0002

Data Index: 579598 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0453. Min Act: -0.0002

Data Index: 484017 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0429. Min Act: -0.0002

Data Index: 712333 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0415. Min Act: -0.0002

Data Index: 538341 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1133590 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0433. Min Act: -0.0002

Data Index: 575668 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1168366 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1257484 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0404. Min Act: -0.0002

Data Index: 890098 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0427. Min Act: -0.0002

Data Index: 213893 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0406. Min Act: -0.0002

Data Index: 950149 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1316017 (C4 (Web Text))

Max Activating Token Index: 465