Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0002

Data Index: 395225 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0648. Min Act: -0.0002

Data Index: 115197 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1008386 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0554. Min Act: -0.0002

Data Index: 949320 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1176377 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1136112 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0458. Min Act: -0.0002

Data Index: 355759 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1189241 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1332371 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0367. Min Act: -0.0002

Data Index: 90552 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1084788 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1428466 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0369. Min Act: -0.0002

Data Index: 343498 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0368. Min Act: -0.0002

Data Index: 558245 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1001429 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0368. Min Act: -0.0002

Data Index: 226773 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0355. Min Act: -0.0002

Data Index: 265819 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1467835 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0352. Min Act: -0.0002

Data Index: 585555 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1360262 (Python Code)

Max Activating Token Index: 21