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

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

Neuron 1892 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3999. Min Range: -2.3999

Max Act: 2.3999. Min Act: -0.0000

Data Index: 305816 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.8268. Min Act: -0.0000

Data Index: 736501 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.6685. Min Act: -0.0000

Data Index: 333683 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.7157. Min Act: -0.0000

Data Index: 836239 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.5501. Min Act: -0.0000

Data Index: 844181 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.7729. Min Act: -0.0000

Data Index: 86300 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.5322. Min Act: -0.0000

Data Index: 102694 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.4342. Min Act: -0.0000

Data Index: 342312 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.3955. Min Act: -0.0000

Data Index: 51230 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1099307 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.3210. Min Act: -0.0000

Data Index: 966015 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1305376 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1128515 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.0537. Min Act: -0.0000

Data Index: 583138 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.0486. Min Act: -0.0000

Data Index: 366336 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.0314. Min Act: -0.0000

Data Index: 178732 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.1150. Min Act: -0.0000

Data Index: 1102305 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 2.3999. Min Range: -2.3999

Max Act: 0.9633. Min Act: -0.0000

Data Index: 107165 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.0154. Min Act: -0.0000

Data Index: 989504 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 2.3999. Min Range: -2.3999

Max Act: 1.0046. Min Act: -0.0000

Data Index: 43698 (C4 (Web Text))

Max Activating Token Index: 401