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

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

Neuron 4640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1195926 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.6901. Min Act: -0.0000

Data Index: 49141 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1050726 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.5990. Min Act: -0.0000

Data Index: 1304736 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.5253. Min Act: -0.0000

Data Index: 572985 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1267351 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.4641. Min Act: -0.0000

Data Index: 864895 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3971. Min Act: -0.0000

Data Index: 703745 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.5174. Min Act: -0.0000

Data Index: 365274 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3453. Min Act: -0.0000

Data Index: 202634 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1059277 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3595. Min Act: -0.0000

Data Index: 236590 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2773. Min Act: -0.0000

Data Index: 968683 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2753. Min Act: -0.0000

Data Index: 293395 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1083497 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1084651 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2604. Min Act: -0.0000

Data Index: 192588 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3255. Min Act: -0.0000

Data Index: 29440 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3255. Min Act: -0.0000

Data Index: 764270 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1334648 (C4 (Web Text))

Max Activating Token Index: 459