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

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

Neuron 5346 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0631. Min Range: -3.0631

Max Act: 3.0631. Min Act: -0.0000

Data Index: 1290533 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.7473. Min Act: -0.0000

Data Index: 485707 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.5365. Min Act: -0.0000

Data Index: 531020 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.5041. Min Act: -0.0000

Data Index: 364233 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.4578. Min Act: -0.0000

Data Index: 812944 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.3939. Min Act: -0.0000

Data Index: 915083 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.6206. Min Act: -0.0000

Data Index: 217703 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.3264. Min Act: -0.0000

Data Index: 38794 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.1975. Min Act: -0.0000

Data Index: 284377 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.1170. Min Act: -0.0000

Data Index: 887180 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.2216. Min Act: -0.0000

Data Index: 1202531 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.2298. Min Act: -0.0000

Data Index: 463920 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.0678. Min Act: -0.0000

Data Index: 709348 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.0395. Min Act: -0.0000

Data Index: 46394 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.0267. Min Act: -0.0000

Data Index: 801977 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.1003. Min Act: -0.0000

Data Index: 920540 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 3.0631. Min Range: -3.0631

Max Act: 2.1147. Min Act: -0.0000

Data Index: 926310 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 3.0631. Min Range: -3.0631

Max Act: 1.8813. Min Act: -0.0000

Data Index: 761442 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 3.0631. Min Range: -3.0631

Max Act: 1.8600. Min Act: -0.0000

Data Index: 1250012 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 3.0631. Min Range: -3.0631

Max Act: 1.7779. Min Act: -0.0000

Data Index: 1130366 (C4 (Web Text))

Max Activating Token Index: 787