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

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

Neuron 1633 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: 1.4517. Min Range: -1.4517

Max Act: 1.4517. Min Act: -0.0001

Data Index: 742427 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3893. Min Act: -0.0001

Data Index: 1181538 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3690. Min Act: -0.0001

Data Index: 845279 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3747. Min Act: -0.0001

Data Index: 649596 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3925. Min Act: -0.0001

Data Index: 1356449 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.4226. Min Act: -0.0001

Data Index: 708093 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3506. Min Act: -0.0001

Data Index: 1326391 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3416. Min Act: -0.0001

Data Index: 149255 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3704. Min Act: -0.0001

Data Index: 891134 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.4084. Min Act: -0.0001

Data Index: 945113 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3162. Min Act: -0.0001

Data Index: 1047366 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3164. Min Act: -0.0001

Data Index: 832075 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2797. Min Act: -0.0001

Data Index: 898260 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3378. Min Act: -0.0001

Data Index: 758089 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2907. Min Act: -0.0001

Data Index: 621452 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3246. Min Act: -0.0001

Data Index: 1097077 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3715. Min Act: -0.0001

Data Index: 1064010 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2853. Min Act: -0.0001

Data Index: 35212 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3221. Min Act: -0.0001

Data Index: 533879 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3155. Min Act: -0.0001

Data Index: 1283504 (C4 (Web Text))

Max Activating Token Index: 23