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

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

Neuron 2735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2260. Min Range: -3.2260

Max Act: 3.0275. Min Act: -0.0001

Data Index: 1349561 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 3.2260. Min Range: -3.2260

Max Act: 3.2260. Min Act: -0.0001

Data Index: 448329 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.7841. Min Act: -0.0001

Data Index: 854116 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.8968. Min Act: -0.0001

Data Index: 645588 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 3.2260. Min Range: -3.2260

Max Act: 3.0578. Min Act: -0.0001

Data Index: 900642 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.9705. Min Act: -0.0001

Data Index: 281393 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.7151. Min Act: -0.0001

Data Index: 5055 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.8391. Min Act: -0.0001

Data Index: 1366568 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 3.2260. Min Range: -3.2260

Max Act: 3.0431. Min Act: -0.0001

Data Index: 1053480 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.6174. Min Act: -0.0001

Data Index: 266547 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.7548. Min Act: -0.0001

Data Index: 187232 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.6719. Min Act: -0.0001

Data Index: 1326484 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.6422. Min Act: -0.0001

Data Index: 1145082 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.7185. Min Act: -0.0001

Data Index: 148552 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.6566. Min Act: -0.0001

Data Index: 696916 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.7380. Min Act: -0.0001

Data Index: 717380 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.7547. Min Act: -0.0001

Data Index: 1220601 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.5618. Min Act: -0.0001

Data Index: 796278 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.4505. Min Act: -0.0001

Data Index: 370823 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 3.2260. Min Range: -3.2260

Max Act: 2.6765. Min Act: -0.0001

Data Index: 19352 (C4 (Web Text))

Max Activating Token Index: 561