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

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

Neuron 1493 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5107. Min Act: -0.0000

Data Index: 581756 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5096. Min Act: -0.0001

Data Index: 1064953 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5322. Min Act: -0.0000

Data Index: 28164 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1173806 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5103. Min Act: -0.0000

Data Index: 890377 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4920. Min Act: -0.0000

Data Index: 173386 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1206820 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1307734 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4920. Min Act: -0.0000

Data Index: 41638 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1114880 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4572. Min Act: -0.0001

Data Index: 701630 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4429. Min Act: -0.0000

Data Index: 524655 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1327491 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1170400 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4173. Min Act: -0.0000

Data Index: 789648 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4097. Min Act: -0.0000

Data Index: 15040 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4200. Min Act: -0.0000

Data Index: 907225 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4201. Min Act: -0.0000

Data Index: 105623 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1038858 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3716. Min Act: -0.0000

Data Index: 938708 (C4 (Web Text))

Max Activating Token Index: 354