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

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

Neuron 4803 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: 3.1352. Min Range: -3.1352

Max Act: 3.0920. Min Act: -0.0000

Data Index: 644090 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 3.1352. Min Range: -3.1352

Max Act: 3.1352. Min Act: -0.0000

Data Index: 165762 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.6532. Min Act: -0.0000

Data Index: 315604 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.5926. Min Act: -0.0000

Data Index: 127129 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.5111. Min Act: -0.0000

Data Index: 514897 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.3647. Min Act: -0.0000

Data Index: 364647 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.1832. Min Act: -0.0000

Data Index: 1120725 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1086724 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.8502. Min Act: -0.0000

Data Index: 565730 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.8675. Min Act: -0.0000

Data Index: 461509 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.0002. Min Act: -0.0000

Data Index: 1189372 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.9821. Min Act: -0.0000

Data Index: 906419 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.9384. Min Act: -0.0000

Data Index: 711693 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.0353. Min Act: -0.0000

Data Index: 1039987 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.9405. Min Act: -0.0000

Data Index: 124341 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.1487. Min Act: -0.0000

Data Index: 167695 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.9066. Min Act: -0.0000

Data Index: 237478 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.9795. Min Act: -0.0000

Data Index: 474167 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 3.1352. Min Range: -3.1352

Max Act: 2.1027. Min Act: -0.0000

Data Index: 975206 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 3.1352. Min Range: -3.1352

Max Act: 1.7313. Min Act: -0.0000

Data Index: 485411 (C4 (Web Text))

Max Activating Token Index: 274