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

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

Neuron 1303 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: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1164013 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0389. Min Act: -0.0002

Data Index: 626540 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1189557 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0369. Min Act: -0.0002

Data Index: 57966 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0372. Min Act: -0.0002

Data Index: 800767 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0357. Min Act: -0.0002

Data Index: 122927 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1220796 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1165907 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0356. Min Act: -0.0002

Data Index: 779499 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0348. Min Act: -0.0002

Data Index: 374072 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0357. Min Act: -0.0002

Data Index: 57031 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1616749 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0342. Min Act: -0.0002

Data Index: 938548 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1132886 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0345. Min Act: -0.0002

Data Index: 590512 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0346. Min Act: -0.0002

Data Index: 499953 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1608033 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0350. Min Act: -0.0003

Data Index: 831949 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1194621 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0342. Min Act: -0.0003

Data Index: 703513 (C4 (Web Text))

Max Activating Token Index: 756