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

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

Neuron 3232 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2359. Min Range: -1.2359

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1498751 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.8391. Min Act: -0.0000

Data Index: 640822 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.8597. Min Act: -0.0000

Data Index: 864340 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.8264. Min Act: -0.0000

Data Index: 790660 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.8239. Min Act: -0.0000

Data Index: 282702 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.8628. Min Act: -0.0000

Data Index: 696392 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7646. Min Act: -0.0000

Data Index: 759161 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1574326 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7828. Min Act: -0.0000

Data Index: 519322 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1015057 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1268952 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1581280 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7464. Min Act: -0.0000

Data Index: 901992 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7736. Min Act: -0.0000

Data Index: 511115 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1163342 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.6748. Min Act: -0.0000

Data Index: 591171 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.6702. Min Act: -0.0000

Data Index: 296158 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.6799. Min Act: -0.0000

Data Index: 791640 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1299570 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.5854. Min Act: -0.0000

Data Index: 669042 (C4 (Web Text))

Max Activating Token Index: 302