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

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

Neuron 1629 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3353. Min Act: -0.0000

Data Index: 27443 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1423288 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1351344 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1095780 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1564070 (Python Code)

Max Activating Token Index: 664

Text #5

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1486917 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1359990 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1470236 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1187797 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1070968 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1464313 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1451994 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1052730 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2160. Min Act: -0.0000

Data Index: 952768 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1469651 (Python Code)

Max Activating Token Index: 664

Text #15

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1628279 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2273. Min Act: -0.0000

Data Index: 81638 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1053040 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1276367 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1473929 (Python Code)

Max Activating Token Index: 918