Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1089 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0001

Data Index: 185537 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1477. Min Act: -0.0001

Data Index: 117226 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1490. Min Act: -0.0001

Data Index: 196623 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1413. Min Act: -0.0001

Data Index: 111046 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1377033 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1436. Min Act: -0.0001

Data Index: 878301 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1319723 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1294. Min Act: -0.0001

Data Index: 410292 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1392. Min Act: -0.0000

Data Index: 697846 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1382. Min Act: -0.0001

Data Index: 165389 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1299089 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1067388 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1383. Min Act: -0.0001

Data Index: 112514 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1238. Min Act: -0.0001

Data Index: 798412 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1264. Min Act: -0.0001

Data Index: 606020 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1122722 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1393877 (Python Code)

Max Activating Token Index: 525

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1239. Min Act: -0.0000

Data Index: 506071 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1223. Min Act: -0.0001

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1288. Min Act: -0.0001

Data Index: 369158 (C4 (Web Text))

Max Activating Token Index: 202