Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3129 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0001

Data Index: 40331 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1005296 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0540. Min Act: -0.0002

Data Index: 465819 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1169959 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0560. Min Act: -0.0002

Data Index: 660297 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0537. Min Act: -0.0002

Data Index: 561923 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0521. Min Act: -0.0002

Data Index: 339477 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0503. Min Act: -0.0002

Data Index: 96232 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0505. Min Act: -0.0001

Data Index: 549463 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0517. Min Act: -0.0002

Data Index: 604919 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1084057 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1326343 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0472. Min Act: -0.0001

Data Index: 621603 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1208850 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1350255 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0457. Min Act: -0.0002

Data Index: 759791 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0563. Min Act: -0.0001

Data Index: 532769 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0479. Min Act: -0.0002

Data Index: 732377 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1168530 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0469. Min Act: -0.0001

Data Index: 767846 (C4 (Web Text))

Max Activating Token Index: 310