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

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

Neuron 504 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.3492. Min Act: -0.0000

Data Index: 325418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.3067. Min Act: 0.0000

Data Index: 647618 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1178753 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.0186. Min Act: -0.0000

Data Index: 301438 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8758. Min Act: -0.0000

Data Index: 95733 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1306796 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1250414 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8437. Min Act: 0.0001

Data Index: 551845 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8010. Min Act: -0.0000

Data Index: 572913 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1209041 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1298037 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7539. Min Act: -0.0000

Data Index: 847559 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7318. Min Act: -0.0000

Data Index: 194959 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7897. Min Act: -0.0000

Data Index: 727454 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7206. Min Act: -0.0000

Data Index: 839141 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7598. Min Act: 0.0000

Data Index: 380550 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7502. Min Act: 0.0000

Data Index: 962131 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7805. Min Act: -0.0000

Data Index: 978434 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1234768 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.7415. Min Act: 0.0000

Data Index: 1045609 (C4 (Web Text))

Max Activating Token Index: 310