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

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

Neuron 2785 in Layer 0

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: 1.2966. Min Range: -1.2966

Max Act: 1.2966. Min Act: -0.0001

Data Index: 1234600 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1927. Min Act: -0.0001

Data Index: 1280713 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1891. Min Act: -0.0001

Data Index: 981755 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1521. Min Act: -0.0002

Data Index: 902336 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1439. Min Act: -0.0001

Data Index: 1354786 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1423. Min Act: -0.0001

Data Index: 761704 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1279. Min Act: -0.0001

Data Index: 709567 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1309. Min Act: -0.0001

Data Index: 443069 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1226. Min Act: -0.0001

Data Index: 187470 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1223. Min Act: -0.0001

Data Index: 643855 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1366. Min Act: -0.0001

Data Index: 704942 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1109. Min Act: -0.0001

Data Index: 639093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1041. Min Act: -0.0001

Data Index: 1022584 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1391. Min Act: -0.0001

Data Index: 1018460 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1274. Min Act: -0.0001

Data Index: 986943 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1073. Min Act: -0.0001

Data Index: 939126 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1177. Min Act: -0.0001

Data Index: 897747 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1212. Min Act: -0.0001

Data Index: 537940 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1167. Min Act: -0.0001

Data Index: 1067916 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0916. Min Act: -0.0001

Data Index: 1259403 (C4 (Web Text))

Max Activating Token Index: 887