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

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

Neuron 4921 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5619. Min Range: -3.5619

Max Act: 3.5619. Min Act: -0.0000

Data Index: 1005807 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 3.5619. Min Range: -3.5619

Max Act: 3.3481. Min Act: -0.0000

Data Index: 1179974 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.5619. Min Range: -3.5619

Max Act: 3.3472. Min Act: -0.0000

Data Index: 50250 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 3.5619. Min Range: -3.5619

Max Act: 3.2208. Min Act: -0.0000

Data Index: 867860 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 3.5619. Min Range: -3.5619

Max Act: 2.7849. Min Act: -0.0000

Data Index: 902866 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.5619. Min Range: -3.5619

Max Act: 2.6550. Min Act: -0.0000

Data Index: 1022892 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 3.5619. Min Range: -3.5619

Max Act: 2.8928. Min Act: -0.0000

Data Index: 1323482 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 3.5619. Min Range: -3.5619

Max Act: 2.6492. Min Act: -0.0000

Data Index: 45341 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 3.5619. Min Range: -3.5619

Max Act: 2.1124. Min Act: -0.0000

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.8008. Min Act: -0.0000

Data Index: 45801 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1004860 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.8473. Min Act: -0.0000

Data Index: 978264 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.7183. Min Act: -0.0000

Data Index: 477870 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.6476. Min Act: -0.0000

Data Index: 899022 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.7362. Min Act: -0.0000

Data Index: 953719 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.7016. Min Act: -0.0000

Data Index: 558696 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.7157. Min Act: -0.0000

Data Index: 1162182 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.5199. Min Act: -0.0000

Data Index: 894397 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1075054 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 3.5619. Min Range: -3.5619

Max Act: 1.6789. Min Act: -0.0000

Data Index: 939229 (C4 (Web Text))

Max Activating Token Index: 205