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

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

Neuron 3507 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.9137. Min Act: -0.0000

Data Index: 848114 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 2.0810. Min Range: -2.0810

Max Act: 2.0810. Min Act: -0.0000

Data Index: 1051146 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.8235. Min Act: -0.0000

Data Index: 888014 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.5946. Min Act: -0.0000

Data Index: 670734 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.6285. Min Act: -0.0000

Data Index: 995173 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.3508. Min Act: -0.0000

Data Index: 375678 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.4786. Min Act: -0.0000

Data Index: 898961 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1130999 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.4215. Min Act: -0.0000

Data Index: 1309240 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.3327. Min Act: -0.0000

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.3372. Min Act: -0.0000

Data Index: 982637 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1299456 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.1517. Min Act: -0.0000

Data Index: 86961 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.4048. Min Act: -0.0000

Data Index: 427520 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.4688. Min Act: -0.0000

Data Index: 800903 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.2198. Min Act: -0.0000

Data Index: 157989 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.1929. Min Act: -0.0000

Data Index: 469761 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.4275. Min Act: -0.0000

Data Index: 742691 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.2401. Min Act: -0.0000

Data Index: 474919 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 2.0810. Min Range: -2.0810

Max Act: 1.0998. Min Act: -0.0000

Data Index: 897624 (C4 (Web Text))

Max Activating Token Index: 677