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

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

Neuron 5538 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1362900 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0447. Min Act: -0.0000

Data Index: 299217 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1628722 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1583784 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0383. Min Act: -0.0000

Data Index: 805019 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0394. Min Act: -0.0000

Data Index: 80943 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0000

Data Index: 624616 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1436643 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1359520 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0400. Min Act: -0.0000

Data Index: 49730 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0416. Min Act: -0.0000

Data Index: 838984 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1395521 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0401. Min Act: -0.0000

Data Index: 283458 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1020380 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1388969 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0332. Min Act: -0.0000

Data Index: 1244068 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0355. Min Act: -0.0000

Data Index: 254916 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1547862 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1496253 (Python Code)

Max Activating Token Index: 948

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0352. Min Act: -0.0000

Data Index: 292187 (C4 (Web Text))

Max Activating Token Index: 216