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

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

Neuron 4614 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1203. Min Range: -1.1203

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1300317 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.9571. Min Act: -0.0000

Data Index: 926148 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.9735. Min Act: -0.0000

Data Index: 476367 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8743. Min Act: -0.0000

Data Index: 674757 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1152252 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8730. Min Act: -0.0000

Data Index: 638730 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8815. Min Act: -0.0000

Data Index: 66340 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8402. Min Act: -0.0000

Data Index: 511024 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8147. Min Act: -0.0000

Data Index: 710606 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7109. Min Act: -0.0000

Data Index: 827511 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7742. Min Act: -0.0000

Data Index: 695785 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1581307 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1074634 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7424. Min Act: -0.0000

Data Index: 351563 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7223. Min Act: -0.0000

Data Index: 56173 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1014732 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7030. Min Act: -0.0000

Data Index: 467938 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.6909. Min Act: -0.0000

Data Index: 903030 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7491. Min Act: -0.0000

Data Index: 414045 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1393569 (Python Code)

Max Activating Token Index: 69