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

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

Neuron 5180 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: 2.6230. Min Range: -2.6230

Max Act: 2.6230. Min Act: -0.0000

Data Index: 298238 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.3530. Min Act: -0.0000

Data Index: 137904 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.1535. Min Act: -0.0000

Data Index: 788208 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.1331. Min Act: -0.0000

Data Index: 350873 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.0050. Min Act: -0.0000

Data Index: 252415 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.0476. Min Act: -0.0000

Data Index: 319406 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.0416. Min Act: -0.0000

Data Index: 566455 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.9650. Min Act: -0.0000

Data Index: 682576 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.0169. Min Act: -0.0000

Data Index: 1418572 (Python Code)

Max Activating Token Index: 370

Text #9

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.0259. Min Act: -0.0000

Data Index: 97060 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 2.6230. Min Range: -2.6230

Max Act: 2.0168. Min Act: -0.0000

Data Index: 1083454 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.9301. Min Act: -0.0000

Data Index: 312592 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.8753. Min Act: -0.0000

Data Index: 1430105 (Python Code)

Max Activating Token Index: 436

Text #13

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.9771. Min Act: -0.0000

Data Index: 92744 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1370642 (Python Code)

Max Activating Token Index: 945

Text #15

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.9635. Min Act: -0.0000

Data Index: 210837 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.8622. Min Act: -0.0000

Data Index: 1623224 (Python Code)

Max Activating Token Index: 1008

Text #17

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1360181 (Python Code)

Max Activating Token Index: 137

Text #18

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.8222. Min Act: -0.0000

Data Index: 1053369 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 2.6230. Min Range: -2.6230

Max Act: 1.7266. Min Act: -0.0000

Data Index: 157597 (C4 (Web Text))

Max Activating Token Index: 542