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

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

Neuron 5609 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1230. Min Range: -2.1230

Max Act: 2.1230. Min Act: -0.0000

Data Index: 876276 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.9300. Min Act: -0.0000

Data Index: 376239 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8330. Min Act: -0.0000

Data Index: 637585 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 2.1230. Min Range: -2.1230

Max Act: 2.0753. Min Act: -0.0000

Data Index: 266271 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.9825. Min Act: -0.0000

Data Index: 22615 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.7418. Min Act: -0.0000

Data Index: 940649 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8783. Min Act: -0.0000

Data Index: 524011 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8532. Min Act: -0.0000

Data Index: 1243120 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.9427. Min Act: -0.0000

Data Index: 596541 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1189016 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8292. Min Act: -0.0000

Data Index: 889110 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8299. Min Act: -0.0000

Data Index: 146409 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1157198 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8270. Min Act: -0.0000

Data Index: 112878 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.6070. Min Act: -0.0000

Data Index: 962158 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 2.1230. Min Range: -2.1230

Max Act: 2.0077. Min Act: -0.0000

Data Index: 948471 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.7634. Min Act: -0.0000

Data Index: 300162 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.6372. Min Act: -0.0000

Data Index: 704200 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.7193. Min Act: -0.0000

Data Index: 797155 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.7480. Min Act: -0.0000

Data Index: 985600 (C4 (Web Text))

Max Activating Token Index: 364