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

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

Neuron 2638 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: 1.3708. Min Range: -1.3708

Max Act: 1.3708. Min Act: -0.0002

Data Index: 735939 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2969. Min Act: -0.0002

Data Index: 847855 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2928. Min Act: -0.0002

Data Index: 1272493 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2739. Min Act: -0.0002

Data Index: 491475 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2006. Min Act: -0.0002

Data Index: 12373 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1826. Min Act: -0.0002

Data Index: 1205474 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1554. Min Act: -0.0002

Data Index: 1288524 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1629. Min Act: -0.0002

Data Index: 134080 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1394. Min Act: -0.0002

Data Index: 766130 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1507. Min Act: -0.0002

Data Index: 346719 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1507. Min Act: -0.0002

Data Index: 464911 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1454. Min Act: -0.0002

Data Index: 297660 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1651. Min Act: -0.0002

Data Index: 364899 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1414. Min Act: -0.0002

Data Index: 1141569 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1357. Min Act: -0.0002

Data Index: 1023796 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1316. Min Act: -0.0002

Data Index: 504521 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1198. Min Act: -0.0002

Data Index: 911000 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1242. Min Act: -0.0002

Data Index: 208459 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1324. Min Act: -0.0002

Data Index: 269630 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1124. Min Act: -0.0002

Data Index: 867884 (C4 (Web Text))

Max Activating Token Index: 829