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

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

Neuron 3630 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.4121. Min Act: -0.0000

Data Index: 766468 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.6736. Min Act: -0.0000

Data Index: 1174691 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.3955. Min Act: -0.0000

Data Index: 755798 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1168689 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.4291. Min Act: -0.0000

Data Index: 253151 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5066. Min Act: -0.0000

Data Index: 821223 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.4000. Min Act: -0.0000

Data Index: 620833 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.3715. Min Act: -0.0000

Data Index: 174233 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1142948 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.2757. Min Act: -0.0000

Data Index: 866984 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.3351. Min Act: -0.0000

Data Index: 116654 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.2554. Min Act: -0.0000

Data Index: 353567 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.3160. Min Act: -0.0000

Data Index: 756140 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1097356 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1187979 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.2312. Min Act: -0.0000

Data Index: 29500 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.1470. Min Act: -0.0000

Data Index: 535858 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.2126. Min Act: -0.0000

Data Index: 589984 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.2990. Min Act: -0.0000

Data Index: 745456 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.2102. Min Act: -0.0000

Data Index: 204547 (C4 (Web Text))

Max Activating Token Index: 10