Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 37 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.5092. Min Act: -0.0000

Data Index: 613511 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1212430 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4387. Min Act: -0.0000

Data Index: 503180 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4507. Min Act: -0.0000

Data Index: 739002 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4129. Min Act: -0.0000

Data Index: 998393 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1310466 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4323. Min Act: -0.0000

Data Index: 303903 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1525962 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3794. Min Act: -0.0000

Data Index: 703103 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3772. Min Act: -0.0000

Data Index: 552464 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3631. Min Act: -0.0000

Data Index: 749421 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3535. Min Act: -0.0000

Data Index: 497243 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1580216 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3660. Min Act: -0.0000

Data Index: 894739 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1169293 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3615. Min Act: -0.0000

Data Index: 200798 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1404342 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1264582 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1548280 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1420396 (Python Code)

Max Activating Token Index: 660