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

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

Neuron 1329 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.5298. Min Act: -0.0002

Data Index: 1275494 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.5427. Min Act: -0.0003

Data Index: 199808 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.4875. Min Act: -0.0002

Data Index: 227158 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.4635. Min Act: -0.0002

Data Index: 1258999 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.4601. Min Act: -0.0002

Data Index: 934504 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.4532. Min Act: -0.0003

Data Index: 938542 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3950. Min Act: -0.0002

Data Index: 665852 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3852. Min Act: -0.0002

Data Index: 1305065 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3897. Min Act: -0.0002

Data Index: 765552 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3852. Min Act: -0.0002

Data Index: 469000 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3850. Min Act: -0.0002

Data Index: 162463 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3757. Min Act: -0.0002

Data Index: 370692 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3524. Min Act: -0.0002

Data Index: 109395 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3811. Min Act: -0.0002

Data Index: 558651 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3387. Min Act: -0.0003

Data Index: 583240 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3483. Min Act: -0.0002

Data Index: 182072 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3459. Min Act: -0.0003

Data Index: 873642 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3621. Min Act: -0.0002

Data Index: 316133 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3548. Min Act: -0.0002

Data Index: 478651 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.3361. Min Act: -0.0002

Data Index: 494337 (C4 (Web Text))

Max Activating Token Index: 844