Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 271 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.8079. Min Act: -0.0000

Data Index: 258210 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5934. Min Act: -0.0000

Data Index: 489011 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5753. Min Act: -0.0000

Data Index: 234733 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4573. Min Act: -0.0000

Data Index: 469292 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3637. Min Act: -0.0000

Data Index: 753231 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4136. Min Act: -0.0000

Data Index: 398029 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4261. Min Act: -0.0000

Data Index: 908026 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3251. Min Act: -0.0000

Data Index: 278678 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2954. Min Act: -0.0000

Data Index: 264352 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1335102 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2061. Min Act: -0.0000

Data Index: 396739 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2883. Min Act: -0.0000

Data Index: 313899 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2477. Min Act: -0.0000

Data Index: 565882 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1235315 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3883. Min Act: -0.0000

Data Index: 984888 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1315163 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1345322 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2353. Min Act: -0.0000

Data Index: 504134 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2441. Min Act: -0.0000

Data Index: 742963 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4013. Min Act: -0.0000

Data Index: 218186 (C4 (Web Text))

Max Activating Token Index: 860