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

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

Neuron 2835 in Layer 1

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: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0002

Data Index: 362516 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0379. Min Act: -0.0002

Data Index: 792770 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0371. Min Act: -0.0003

Data Index: 701019 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1163215 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0357. Min Act: -0.0002

Data Index: 982953 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0352. Min Act: -0.0002

Data Index: 695235 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0352. Min Act: -0.0002

Data Index: 580746 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0332. Min Act: -0.0002

Data Index: 591048 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1549771 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0337. Min Act: -0.0002

Data Index: 835668 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0337. Min Act: -0.0002

Data Index: 791746 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1327414 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0321. Min Act: -0.0002

Data Index: 934627 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0322. Min Act: -0.0002

Data Index: 875070 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0319. Min Act: -0.0002

Data Index: 404390 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0316. Min Act: -0.0002

Data Index: 531629 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0316. Min Act: -0.0002

Data Index: 682360 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0315. Min Act: -0.0002

Data Index: 751704 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0313. Min Act: -0.0002

Data Index: 767915 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1611689 (Python Code)

Max Activating Token Index: 448