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

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

Neuron 5617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1334466 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1502. Min Act: -0.0000

Data Index: 764531 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1110133 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1635. Min Act: -0.0000

Data Index: 688608 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1630. Min Act: -0.0000

Data Index: 96744 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1423. Min Act: -0.0000

Data Index: 200997 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1244488 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1079065 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1368. Min Act: -0.0001

Data Index: 591608 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1387. Min Act: -0.0001

Data Index: 774913 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1446. Min Act: -0.0000

Data Index: 997411 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1498. Min Act: -0.0001

Data Index: 474006 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1376. Min Act: -0.0000

Data Index: 368482 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1266. Min Act: -0.0000

Data Index: 193423 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1267. Min Act: -0.0000

Data Index: 561534 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1339. Min Act: -0.0001

Data Index: 597366 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1248. Min Act: -0.0000

Data Index: 268685 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1363. Min Act: -0.0000

Data Index: 502311 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1305. Min Act: -0.0000

Data Index: 97543 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1279. Min Act: -0.0000

Data Index: 715481 (C4 (Web Text))

Max Activating Token Index: 811