Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6468. Min Range: -4.6468

Max Act: 4.6468. Min Act: -0.0000

Data Index: 12693 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 4.6468. Min Range: -4.6468

Max Act: 4.3418. Min Act: -0.0000

Data Index: 222061 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 4.6468. Min Range: -4.6468

Max Act: 4.1530. Min Act: -0.0000

Data Index: 288813 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 4.6468. Min Range: -4.6468

Max Act: 4.0375. Min Act: -0.0000

Data Index: 21632 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.8715. Min Act: -0.0000

Data Index: 1327410 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.6191. Min Act: -0.0000

Data Index: 1155792 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.9811. Min Act: -0.0000

Data Index: 913140 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.7214. Min Act: -0.0000

Data Index: 594754 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.3394. Min Act: -0.0000

Data Index: 447581 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.7352. Min Act: -0.0000

Data Index: 595173 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.5883. Min Act: -0.0000

Data Index: 1040488 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.4282. Min Act: -0.0000

Data Index: 61657 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.3746. Min Act: -0.0000

Data Index: 849434 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.3596. Min Act: -0.0000

Data Index: 118741 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.3174. Min Act: -0.0000

Data Index: 755284 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.6149. Min Act: -0.0000

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.3178. Min Act: -0.0001

Data Index: 1078596 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.7274. Min Act: -0.0000

Data Index: 853821 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.1346. Min Act: -0.0000

Data Index: 1038183 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 4.6468. Min Range: -4.6468

Max Act: 3.3689. Min Act: -0.0000

Data Index: 646112 (C4 (Web Text))

Max Activating Token Index: 585