Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4061 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.9469. Min Act: -0.0001

Data Index: 515291 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7871. Min Act: -0.0001

Data Index: 708049 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7896. Min Act: -0.0001

Data Index: 255723 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7253. Min Act: -0.0001

Data Index: 1334367 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7586. Min Act: -0.0001

Data Index: 706771 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8074. Min Act: -0.0001

Data Index: 209268 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6947. Min Act: -0.0001

Data Index: 1180258 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6952. Min Act: -0.0001

Data Index: 190122 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6842. Min Act: -0.0001

Data Index: 1120446 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7131. Min Act: -0.0001

Data Index: 985623 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6097. Min Act: -0.0001

Data Index: 459283 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6678. Min Act: -0.0001

Data Index: 538801 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6074. Min Act: -0.0001

Data Index: 112347 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6231. Min Act: -0.0001

Data Index: 559728 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6214. Min Act: -0.0001

Data Index: 428989 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1289548 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6587. Min Act: -0.0001

Data Index: 66157 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5507. Min Act: -0.0001

Data Index: 1357213 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6231. Min Act: -0.0001

Data Index: 748329 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6136. Min Act: -0.0001

Data Index: 909815 (C4 (Web Text))

Max Activating Token Index: 927