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

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

Neuron 3558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.8339. Min Act: -0.0001

Data Index: 594450 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.5534. Min Act: -0.0001

Data Index: 225932 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.2584. Min Act: -0.0001

Data Index: 1019630 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.2370. Min Act: -0.0001

Data Index: 1008216 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1911. Min Act: -0.0001

Data Index: 819126 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.4561. Min Act: -0.0001

Data Index: 497584 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.2829. Min Act: -0.0001

Data Index: 147158 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.4189. Min Act: -0.0001

Data Index: 981331 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1224. Min Act: -0.0001

Data Index: 964889 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1773. Min Act: -0.0001

Data Index: 922269 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1481. Min Act: -0.0001

Data Index: 593957 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1401. Min Act: -0.0001

Data Index: 284544 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 3.8339. Min Range: -3.8339

Max Act: 2.9731. Min Act: -0.0001

Data Index: 782479 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 3.8339. Min Range: -3.8339

Max Act: 2.8370. Min Act: -0.0001

Data Index: 47154 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1197. Min Act: -0.0001

Data Index: 828099 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.2446. Min Act: -0.0001

Data Index: 678241 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1008. Min Act: -0.0001

Data Index: 1337882 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.8339. Min Range: -3.8339

Max Act: 2.9565. Min Act: -0.0001

Data Index: 1255806 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.1996. Min Act: -0.0001

Data Index: 1242238 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.8339. Min Range: -3.8339

Max Act: 3.3446. Min Act: -0.0001

Data Index: 170676 (C4 (Web Text))

Max Activating Token Index: 926