Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4124 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0471. Min Act: -0.0002

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0462. Min Act: -0.0002

Data Index: 58351 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0443. Min Act: -0.0002

Data Index: 232818 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1449072 (Python Code)

Max Activating Token Index: 1000

Text #4

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1079590 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1468567 (Python Code)

Max Activating Token Index: 437

Text #6

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0437. Min Act: -0.0002

Data Index: 139911 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1616011 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1507013 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1399311 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0415. Min Act: -0.0002

Data Index: 684930 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1377784 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0394. Min Act: -0.0003

Data Index: 896552 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1363836 (Python Code)

Max Activating Token Index: 181

Text #14

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1240814 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0386. Min Act: -0.0002

Data Index: 359724 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1375941 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0383. Min Act: -0.0002

Data Index: 381409 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1408059 (Python Code)

Max Activating Token Index: 248