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

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

Neuron 327 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: 0.0443. Min Range: -0.0443

Max Act: 0.0443. Min Act: -0.0005

Data Index: 1124424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0419. Min Act: -0.0004

Data Index: 218086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0360. Min Act: -0.0005

Data Index: 21664 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0354. Min Act: -0.0005

Data Index: 743916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0357. Min Act: -0.0005

Data Index: 747225 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0351. Min Act: -0.0005

Data Index: 1242289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0351. Min Act: -0.0005

Data Index: 1215013 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0340. Min Act: -0.0005

Data Index: 41426 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1209949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0350. Min Act: -0.0005

Data Index: 1165609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0339. Min Act: -0.0005

Data Index: 322289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0334. Min Act: -0.0005

Data Index: 787426 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0344. Min Act: -0.0005

Data Index: 663094 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0334. Min Act: -0.0005

Data Index: 472917 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0344. Min Act: -0.0005

Data Index: 741047 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0336. Min Act: -0.0005

Data Index: 386480 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1038877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0334. Min Act: -0.0005

Data Index: 187885 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0332. Min Act: -0.0005

Data Index: 692451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0340. Min Act: -0.0004

Data Index: 128442 (C4 (Web Text))

Max Activating Token Index: 1023