Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1749 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0329. Min Act: -0.0006

Data Index: 811700 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0006

Data Index: 308136 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0340. Min Act: -0.0006

Data Index: 797016 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0334. Min Act: -0.0006

Data Index: 250074 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1301930 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0323. Min Act: -0.0006

Data Index: 265248 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1081345 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0314. Min Act: -0.0006

Data Index: 79906 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0307. Min Act: -0.0006

Data Index: 267445 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0304. Min Act: -0.0006

Data Index: 341018 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0306. Min Act: -0.0006

Data Index: 973339 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1022379 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0304. Min Act: -0.0006

Data Index: 226210 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1305660 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0307. Min Act: -0.0006

Data Index: 1317366 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0306. Min Act: -0.0006

Data Index: 713393 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1309206 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1146450 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1357783 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0303. Min Act: -0.0006

Data Index: 179174 (C4 (Web Text))

Max Activating Token Index: 14