Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1372 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.6062. Min Act: -0.0005

Data Index: 1456880 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.6254. Min Act: -0.0005

Data Index: 1477097 (Python Code)

Max Activating Token Index: 583

Text #2

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.5267. Min Act: -0.0005

Data Index: 515982 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4648. Min Act: -0.0005

Data Index: 1423284 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4252. Min Act: -0.0005

Data Index: 1469551 (Python Code)

Max Activating Token Index: 724

Text #5

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4635. Min Act: -0.0005

Data Index: 1593957 (Python Code)

Max Activating Token Index: 979

Text #6

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4469. Min Act: -0.0005

Data Index: 1432964 (Python Code)

Max Activating Token Index: 416

Text #7

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4827. Min Act: -0.0005

Data Index: 1440360 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4485. Min Act: -0.0005

Data Index: 1377315 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4518. Min Act: -0.0005

Data Index: 1586229 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4315. Min Act: -0.0005

Data Index: 1635353 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4291. Min Act: -0.0005

Data Index: 433894 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4550. Min Act: -0.0005

Data Index: 1589641 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4356. Min Act: -0.0005

Data Index: 1505425 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4064. Min Act: -0.0005

Data Index: 1391106 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4346. Min Act: -0.0005

Data Index: 1525092 (Python Code)

Max Activating Token Index: 401

Text #16

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.3883. Min Act: -0.0005

Data Index: 1475678 (Python Code)

Max Activating Token Index: 916

Text #17

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4246. Min Act: -0.0005

Data Index: 1376261 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4200. Min Act: -0.0005

Data Index: 1456694 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 0.6254. Min Range: -0.6254

Max Act: 0.4178. Min Act: -0.0005

Data Index: 1482250 (Python Code)

Max Activating Token Index: 802