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

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

Neuron 1234 in Layer 3

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: 0.0472. Min Act: -0.0001

Data Index: 727750 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0406. Min Act: -0.0001

Data Index: 623464 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0388. Min Act: -0.0001

Data Index: 924255 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0378. Min Act: -0.0001

Data Index: 509935 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0333. Min Act: -0.0001

Data Index: 449833 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0333. Min Act: -0.0001

Data Index: 665244 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0330. Min Act: -0.0001

Data Index: 4028 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0341. Min Act: -0.0001

Data Index: 741633 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1155780 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0339. Min Act: -0.0001

Data Index: 46961 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0320. Min Act: -0.0001

Data Index: 995047 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1284433 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1297255 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0330. Min Act: -0.0001

Data Index: 918392 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0309. Min Act: -0.0001

Data Index: 843903 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1314174 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0330. Min Act: -0.0001

Data Index: 929730 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1073157 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0291. Min Act: -0.0001

Data Index: 701368 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0308. Min Act: -0.0001

Data Index: 507278 (C4 (Web Text))

Max Activating Token Index: 773