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

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

Neuron 2619 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.5326. Min Act: -0.0001

Data Index: 1158128 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2087. Min Act: -0.0001

Data Index: 116465 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2080. Min Act: -0.0001

Data Index: 714720 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.3371. Min Act: -0.0001

Data Index: 388304 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2474. Min Act: -0.0001

Data Index: 475283 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2532. Min Act: -0.0001

Data Index: 308858 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2580. Min Act: -0.0001

Data Index: 810821 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2764. Min Act: -0.0001

Data Index: 28912 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2367. Min Act: -0.0001

Data Index: 50705 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1784. Min Act: -0.0001

Data Index: 880670 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2099. Min Act: -0.0001

Data Index: 720633 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1438. Min Act: -0.0001

Data Index: 654924 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2400. Min Act: -0.0001

Data Index: 166399 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1939. Min Act: -0.0001

Data Index: 37163 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1191. Min Act: -0.0001

Data Index: 387131 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1411. Min Act: -0.0001

Data Index: 842208 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1462. Min Act: -0.0001

Data Index: 514942 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.0082. Min Act: -0.0001

Data Index: 190579 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1373. Min Act: -0.0001

Data Index: 1049347 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1328. Min Act: -0.0001

Data Index: 346636 (C4 (Web Text))

Max Activating Token Index: 59