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

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

Neuron 353 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.2490. Min Act: -0.0000

Data Index: 1334429 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1226179 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.9230. Min Act: -0.0000

Data Index: 667824 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.1324. Min Act: -0.0000

Data Index: 767676 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.6693. Min Act: -0.0000

Data Index: 994428 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7414. Min Act: -0.0000

Data Index: 1160904 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.0681. Min Act: -0.0000

Data Index: 1002924 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.0353. Min Act: -0.0000

Data Index: 241779 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.0064. Min Act: -0.0000

Data Index: 215036 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.1329. Min Act: -0.0000

Data Index: 1111999 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7483. Min Act: -0.0000

Data Index: 367994 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7675. Min Act: -0.0000

Data Index: 956424 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7815. Min Act: -0.0000

Data Index: 1343876 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.8793. Min Act: -0.0000

Data Index: 734279 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7150. Min Act: -0.0000

Data Index: 738436 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7327. Min Act: -0.0000

Data Index: 430042 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1214604 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.8135. Min Act: -0.0000

Data Index: 87941 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7167. Min Act: -0.0000

Data Index: 443770 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.6877. Min Act: -0.0000

Data Index: 562296 (C4 (Web Text))

Max Activating Token Index: 92