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

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

Neuron 1348 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5213. Min Range: -6.5213

Max Act: 6.5213. Min Act: -0.0001

Data Index: 212961 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 6.5213. Min Range: -6.5213

Max Act: 5.6422. Min Act: -0.0001

Data Index: 524289 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 6.5213. Min Range: -6.5213

Max Act: 5.5603. Min Act: -0.0001

Data Index: 1273154 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 6.5213. Min Range: -6.5213

Max Act: 5.3507. Min Act: -0.0000

Data Index: 507444 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 6.5213. Min Range: -6.5213

Max Act: 5.7080. Min Act: -0.0001

Data Index: 175171 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 6.5213. Min Range: -6.5213

Max Act: 5.3302. Min Act: -0.0001

Data Index: 1079194 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 6.5213. Min Range: -6.5213

Max Act: 4.8332. Min Act: -0.0001

Data Index: 237944 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 6.5213. Min Range: -6.5213

Max Act: 4.4958. Min Act: -0.0001

Data Index: 69302 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.8613. Min Act: -0.0001

Data Index: 420446 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 6.5213. Min Range: -6.5213

Max Act: 4.0322. Min Act: -0.0001

Data Index: 801559 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.9737. Min Act: -0.0001

Data Index: 995140 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.9798. Min Act: -0.0000

Data Index: 732370 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.7199. Min Act: -0.0001

Data Index: 1190432 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.6227. Min Act: -0.0001

Data Index: 263723 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.7111. Min Act: -0.0000

Data Index: 498942 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.3906. Min Act: -0.0001

Data Index: 338380 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.4204. Min Act: -0.0000

Data Index: 843281 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.5114. Min Act: -0.0000

Data Index: 151140 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.2593. Min Act: -0.0001

Data Index: 324734 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 6.5213. Min Range: -6.5213

Max Act: 3.3961. Min Act: -0.0000

Data Index: 1031669 (C4 (Web Text))

Max Activating Token Index: 918