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

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

Neuron 4289 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.4456. Min Act: -0.0000

Data Index: 442069 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.5040. Min Act: -0.0000

Data Index: 117147 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.2847. Min Act: -0.0000

Data Index: 684331 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1025309 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.2602. Min Act: -0.0000

Data Index: 177127 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1086034 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1639. Min Act: -0.0000

Data Index: 750945 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1183. Min Act: -0.0000

Data Index: 747216 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1222168 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1617. Min Act: -0.0000

Data Index: 323491 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1183. Min Act: -0.0000

Data Index: 523903 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0386. Min Act: -0.0000

Data Index: 577582 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1178309 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0056. Min Act: -0.0000

Data Index: 451100 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.5040. Min Range: -1.5040

Max Act: 0.9522. Min Act: -0.0000

Data Index: 80494 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0710. Min Act: -0.0000

Data Index: 368399 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.5040. Min Range: -1.5040

Max Act: 0.9010. Min Act: -0.0000

Data Index: 266002 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1297602 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0195. Min Act: -0.0000

Data Index: 325524 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0162. Min Act: -0.0000

Data Index: 756546 (C4 (Web Text))

Max Activating Token Index: 849