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

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

Neuron 656 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0002

Data Index: 92844 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0512. Min Act: -0.0002

Data Index: 939409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0437. Min Act: -0.0002

Data Index: 819158 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0431. Min Act: -0.0003

Data Index: 380052 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0377. Min Act: -0.0002

Data Index: 962669 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0388. Min Act: -0.0002

Data Index: 517745 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0381. Min Act: -0.0002

Data Index: 801137 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0372. Min Act: -0.0002

Data Index: 225818 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0368. Min Act: -0.0002

Data Index: 627618 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0373. Min Act: -0.0002

Data Index: 239598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1021315 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0365. Min Act: -0.0002

Data Index: 846541 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0356. Min Act: -0.0002

Data Index: 650147 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1313140 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0355. Min Act: -0.0002

Data Index: 165256 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1256779 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1202371 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0330. Min Act: -0.0002

Data Index: 25168 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0324. Min Act: -0.0002

Data Index: 362336 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1095078 (C4 (Web Text))

Max Activating Token Index: 863