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

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

Neuron 2272 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3458. Min Act: 0.0000

Data Index: 1094780 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3038. Min Act: 0.0000

Data Index: 1255062 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2970. Min Act: 0.0000

Data Index: 1316472 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2741. Min Act: 0.0001

Data Index: 29328 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2775. Min Act: 0.0001

Data Index: 1150910 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2458. Min Act: 0.0001

Data Index: 800597 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2453. Min Act: 0.0000

Data Index: 1510906 (Python Code)

Max Activating Token Index: 804

Text #7

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2543. Min Act: 0.0001

Data Index: 378942 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2587. Min Act: 0.0001

Data Index: 1036538 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2407. Min Act: 0.0001

Data Index: 1136721 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2441. Min Act: 0.0001

Data Index: 775667 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2515. Min Act: 0.0001

Data Index: 1257229 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2317. Min Act: 0.0001

Data Index: 926766 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2312. Min Act: 0.0001

Data Index: 880095 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2407. Min Act: 0.0001

Data Index: 1296729 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2280. Min Act: 0.0000

Data Index: 1167915 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2346. Min Act: 0.0000

Data Index: 965089 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2257. Min Act: 0.0000

Data Index: 534656 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2338. Min Act: 0.0001

Data Index: 985845 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2282. Min Act: 0.0000

Data Index: 997035 (C4 (Web Text))

Max Activating Token Index: 379