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

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

Neuron 3343 in Layer 0

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: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1145722 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0444. Min Act: -0.0001

Data Index: 416599 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1123750 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0406. Min Act: -0.0001

Data Index: 552095 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0396. Min Act: -0.0001

Data Index: 56281 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0393. Min Act: -0.0001

Data Index: 388020 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0395. Min Act: -0.0002

Data Index: 735698 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0398. Min Act: -0.0001

Data Index: 442962 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1355578 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0386. Min Act: -0.0001

Data Index: 119268 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1138441 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0380. Min Act: -0.0001

Data Index: 714346 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1286806 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0376. Min Act: -0.0001

Data Index: 651897 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0383. Min Act: -0.0001

Data Index: 837181 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0390. Min Act: -0.0001

Data Index: 256427 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0375. Min Act: -0.0002

Data Index: 66562 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0378. Min Act: -0.0001

Data Index: 497416 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0377. Min Act: -0.0001

Data Index: 876144 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0385. Min Act: -0.0001

Data Index: 342823 (C4 (Web Text))

Max Activating Token Index: 935