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

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

Neuron 1950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1070207 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0480. Min Act: -0.0001

Data Index: 20351 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1625691 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1290251 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0459. Min Act: -0.0001

Data Index: 437017 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1005916 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0437. Min Act: -0.0001

Data Index: 129058 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1531645 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0433. Min Act: -0.0000

Data Index: 1359858 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0406. Min Act: -0.0001

Data Index: 521837 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0467. Min Act: -0.0001

Data Index: 563220 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1089416 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1175595 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1064366 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0417. Min Act: -0.0001

Data Index: 470494 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0419. Min Act: -0.0001

Data Index: 51709 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1316647 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1477152 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0403. Min Act: -0.0001

Data Index: 515539 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0379. Min Act: -0.0001

Data Index: 233972 (C4 (Web Text))

Max Activating Token Index: 216