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

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

Neuron 1646 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0935. Min Range: -2.0935

Max Act: 2.0935. Min Act: -0.0000

Data Index: 867188 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1225202 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1208304 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.2447. Min Act: -0.0000

Data Index: 150093 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.2395. Min Act: 0.0000

Data Index: 1114560 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.1657. Min Act: -0.0000

Data Index: 46981 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.1416. Min Act: 0.0000

Data Index: 711299 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.1221. Min Act: -0.0000

Data Index: 352613 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.0827. Min Act: 0.0000

Data Index: 922533 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.1292. Min Act: -0.0000

Data Index: 87336 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.0375. Min Act: 0.0000

Data Index: 891981 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.0373. Min Act: -0.0000

Data Index: 415670 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 2.0935. Min Range: -2.0935

Max Act: 1.0013. Min Act: -0.0000

Data Index: 33136 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.0935. Min Range: -2.0935

Max Act: 0.9978. Min Act: 0.0000

Data Index: 88225 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 2.0935. Min Range: -2.0935

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1053314 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 2.0935. Min Range: -2.0935

Max Act: 0.9810. Min Act: -0.0000

Data Index: 26423 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 2.0935. Min Range: -2.0935

Max Act: 0.9702. Min Act: -0.0000

Data Index: 311852 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 2.0935. Min Range: -2.0935

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1265273 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 2.0935. Min Range: -2.0935

Max Act: 0.9582. Min Act: -0.0000

Data Index: 69226 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 2.0935. Min Range: -2.0935

Max Act: 0.9444. Min Act: -0.0000

Data Index: 283823 (C4 (Web Text))

Max Activating Token Index: 636