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

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

Neuron 5354 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2268. Min Act: -0.0000

Data Index: 236329 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.3390. Min Act: -0.0000

Data Index: 895922 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2717. Min Act: -0.0000

Data Index: 235993 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.3756. Min Act: -0.0000

Data Index: 737077 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2334. Min Act: -0.0000

Data Index: 307197 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2898. Min Act: -0.0000

Data Index: 385102 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1698. Min Act: -0.0000

Data Index: 98111 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2361. Min Act: -0.0000

Data Index: 750892 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.2588. Min Act: -0.0000

Data Index: 801202 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1054. Min Act: -0.0000

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0467. Min Act: -0.0000

Data Index: 104697 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1158686 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1121511 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.1193. Min Act: -0.0000

Data Index: 387230 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0731. Min Act: -0.0000

Data Index: 691446 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0891. Min Act: -0.0000

Data Index: 155578 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0925. Min Act: -0.0000

Data Index: 796091 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1362568 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 1.3756. Min Range: -1.3756

Max Act: 1.0214. Min Act: -0.0000

Data Index: 665201 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 1.3756. Min Range: -1.3756

Max Act: 0.9446. Min Act: -0.0000

Data Index: 954549 (C4 (Web Text))

Max Activating Token Index: 541