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

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

Neuron 5286 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.6238. Min Act: -0.0000

Data Index: 810758 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.4490. Min Act: -0.0000

Data Index: 788952 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.1957. Min Act: -0.0000

Data Index: 64464 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.5041. Min Act: -0.0000

Data Index: 750783 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1292381 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.9696. Min Act: -0.0000

Data Index: 353219 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.1733. Min Act: -0.0000

Data Index: 1080540 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.1045. Min Act: -0.0000

Data Index: 530269 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.9667. Min Act: -0.0000

Data Index: 554382 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.9318. Min Act: -0.0000

Data Index: 1059068 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 2.6238. Min Range: -2.6238

Max Act: 2.0419. Min Act: -0.0000

Data Index: 874766 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.9291. Min Act: -0.0000

Data Index: 431003 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.9787. Min Act: -0.0000

Data Index: 485251 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1359686 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.9121. Min Act: -0.0000

Data Index: 293747 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.7691. Min Act: -0.0000

Data Index: 33318 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.8371. Min Act: -0.0000

Data Index: 827469 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.8362. Min Act: -0.0000

Data Index: 869386 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.8402. Min Act: -0.0000

Data Index: 247196 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 2.6238. Min Range: -2.6238

Max Act: 1.7680. Min Act: -0.0000

Data Index: 757095 (C4 (Web Text))

Max Activating Token Index: 158