Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1211510 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1142571 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1329171 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3565. Min Act: -0.0000

Data Index: 89752 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3767. Min Act: -0.0000

Data Index: 426353 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3453. Min Act: -0.0000

Data Index: 627899 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1106893 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3457. Min Act: -0.0000

Data Index: 249921 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1014551 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3385. Min Act: -0.0000

Data Index: 946581 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3528. Min Act: -0.0000

Data Index: 171121 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3166. Min Act: -0.0000

Data Index: 649460 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3303. Min Act: -0.0000

Data Index: 57551 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3208. Min Act: -0.0001

Data Index: 373514 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3300. Min Act: -0.0000

Data Index: 592139 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3268. Min Act: -0.0000

Data Index: 750900 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1191056 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3350. Min Act: -0.0000

Data Index: 915415 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3132. Min Act: -0.0000

Data Index: 686469 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3238. Min Act: -0.0000

Data Index: 336553 (C4 (Web Text))

Max Activating Token Index: 588