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

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

Neuron 1608 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: 0.1666. Min Range: -0.1666

Max Act: 0.1666. Min Act: -0.0002

Data Index: 1011801 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1536. Min Act: -0.0002

Data Index: 401046 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1519. Min Act: -0.0002

Data Index: 1179045 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1454. Min Act: -0.0002

Data Index: 260152 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1453. Min Act: -0.0003

Data Index: 353213 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1421. Min Act: -0.0002

Data Index: 978491 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1416. Min Act: -0.0002

Data Index: 918314 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1397. Min Act: -0.0002

Data Index: 1289590 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1434. Min Act: -0.0002

Data Index: 890779 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1128698 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1397. Min Act: -0.0002

Data Index: 102679 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1359. Min Act: -0.0002

Data Index: 526617 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1362. Min Act: -0.0002

Data Index: 966124 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1391. Min Act: -0.0002

Data Index: 239963 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1344. Min Act: -0.0002

Data Index: 250764 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1355. Min Act: -0.0002

Data Index: 310658 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1374. Min Act: -0.0002

Data Index: 313020 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1335. Min Act: -0.0002

Data Index: 92254 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1333. Min Act: -0.0002

Data Index: 1034829 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1019198 (C4 (Web Text))

Max Activating Token Index: 210