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

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

Neuron 1849 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: 1.3145. Min Range: -1.3145

Max Act: 1.3145. Min Act: -0.0002

Data Index: 765485 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2691. Min Act: -0.0002

Data Index: 1155969 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2517. Min Act: -0.0002

Data Index: 876255 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2472. Min Act: -0.0002

Data Index: 562280 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2399. Min Act: -0.0002

Data Index: 1159824 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2196. Min Act: -0.0002

Data Index: 276116 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2150. Min Act: -0.0002

Data Index: 87660 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1971. Min Act: -0.0002

Data Index: 662257 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1788. Min Act: -0.0003

Data Index: 245781 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1767. Min Act: -0.0002

Data Index: 838808 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1710. Min Act: -0.0002

Data Index: 218887 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1602. Min Act: -0.0002

Data Index: 381863 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1335. Min Act: -0.0002

Data Index: 406633 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1629. Min Act: -0.0002

Data Index: 708717 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1481. Min Act: -0.0002

Data Index: 365595 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1284. Min Act: -0.0002

Data Index: 607658 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1376. Min Act: -0.0002

Data Index: 716738 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1104. Min Act: -0.0002

Data Index: 298306 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1252. Min Act: -0.0002

Data Index: 1074353 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.0970. Min Act: -0.0002

Data Index: 416690 (C4 (Web Text))

Max Activating Token Index: 163