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

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

Neuron 3746 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9276. Min Range: -4.9276

Max Act: 4.9276. Min Act: -0.0000

Data Index: 492099 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 4.9276. Min Range: -4.9276

Max Act: 3.4179. Min Act: -0.0000

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 4.9276. Min Range: -4.9276

Max Act: 2.4961. Min Act: 0.0000

Data Index: 294141 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 4.9276. Min Range: -4.9276

Max Act: 2.2209. Min Act: -0.0000

Data Index: 86793 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 4.9276. Min Range: -4.9276

Max Act: 2.1270. Min Act: -0.0000

Data Index: 785765 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 4.9276. Min Range: -4.9276

Max Act: 2.2018. Min Act: 0.0001

Data Index: 715493 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 4.9276. Min Range: -4.9276

Max Act: 2.0031. Min Act: 0.0000

Data Index: 1301404 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.9697. Min Act: 0.0000

Data Index: 968447 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.9671. Min Act: 0.0000

Data Index: 881041 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.9694. Min Act: -0.0000

Data Index: 70481 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.8170. Min Act: 0.0000

Data Index: 285898 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.7410. Min Act: -0.0000

Data Index: 1282176 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.6035. Min Act: 0.0000

Data Index: 587028 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.6032. Min Act: 0.0000

Data Index: 220165 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.5927. Min Act: -0.0000

Data Index: 338790 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1491535 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.5959. Min Act: 0.0000

Data Index: 1190924 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.5997. Min Act: 0.0000

Data Index: 40169 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.5986. Min Act: -0.0000

Data Index: 1070364 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 4.9276. Min Range: -4.9276

Max Act: 1.4781. Min Act: -0.0000

Data Index: 368126 (C4 (Web Text))

Max Activating Token Index: 17