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

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

Neuron 1425 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: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0001

Data Index: 528211 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1290923 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0424. Min Act: -0.0001

Data Index: 630133 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1003304 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1024514 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0400. Min Act: -0.0002

Data Index: 488460 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1066744 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1032689 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0347. Min Act: -0.0001

Data Index: 709125 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0346. Min Act: -0.0002

Data Index: 744900 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0349. Min Act: -0.0001

Data Index: 499010 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0350. Min Act: -0.0001

Data Index: 532534 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0362. Min Act: -0.0001

Data Index: 724320 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1049310 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1142469 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0329. Min Act: -0.0002

Data Index: 94162 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0339. Min Act: -0.0002

Data Index: 450220 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0326. Min Act: -0.0002

Data Index: 262284 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0341. Min Act: -0.0001

Data Index: 476448 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0310. Min Act: -0.0002

Data Index: 308293 (C4 (Web Text))

Max Activating Token Index: 792