Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0003

Data Index: 177278 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1448170 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0380. Min Act: -0.0003

Data Index: 893996 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0359. Min Act: -0.0003

Data Index: 173563 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0349. Min Act: -0.0003

Data Index: 410584 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0387. Min Act: -0.0003

Data Index: 531034 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0337. Min Act: -0.0003

Data Index: 712242 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0372. Min Act: -0.0002

Data Index: 794943 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1113709 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0324. Min Act: -0.0003

Data Index: 646015 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0329. Min Act: -0.0004

Data Index: 376790 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0333. Min Act: -0.0003

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0305. Min Act: -0.0003

Data Index: 652087 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0336. Min Act: -0.0003

Data Index: 729835 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0318. Min Act: -0.0003

Data Index: 464671 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0313. Min Act: -0.0003

Data Index: 952249 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1365897 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0316. Min Act: -0.0003

Data Index: 878553 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1238889 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0294. Min Act: -0.0003

Data Index: 843419 (C4 (Web Text))

Max Activating Token Index: 1023