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

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

Neuron 4180 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.7387. Min Act: -0.0000

Data Index: 255224 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.8363. Min Act: 0.0000

Data Index: 796429 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.6073. Min Act: 0.0000

Data Index: 292624 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.4213. Min Act: 0.0000

Data Index: 1025959 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3542. Min Act: 0.0000

Data Index: 827781 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3550. Min Act: -0.0000

Data Index: 632276 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3569. Min Act: -0.0000

Data Index: 1168224 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.4605. Min Act: 0.0000

Data Index: 739252 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3278. Min Act: 0.0000

Data Index: 313278 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3090. Min Act: 0.0001

Data Index: 273494 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.1546. Min Act: 0.0000

Data Index: 857919 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.2647. Min Act: 0.0000

Data Index: 1143290 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.2349. Min Act: 0.0000

Data Index: 1217500 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3471. Min Act: -0.0000

Data Index: 105997 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3351. Min Act: 0.0000

Data Index: 202252 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.1196. Min Act: 0.0000

Data Index: 133857 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.2345. Min Act: 0.0001

Data Index: 1267631 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.1247. Min Act: 0.0001

Data Index: 65193 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.0958. Min Act: -0.0000

Data Index: 692289 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.0792. Min Act: -0.0000

Data Index: 874540 (C4 (Web Text))

Max Activating Token Index: 517