Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.8143. Min Act: -0.0000

Data Index: 80979 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7714. Min Act: -0.0000

Data Index: 974681 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7612. Min Act: -0.0000

Data Index: 799464 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7767. Min Act: -0.0000

Data Index: 243683 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7281. Min Act: -0.0000

Data Index: 36721 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7011. Min Act: -0.0000

Data Index: 505046 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1121891 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1125672 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6675. Min Act: -0.0000

Data Index: 108290 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7907. Min Act: -0.0000

Data Index: 323657 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1122555 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6559. Min Act: -0.0000

Data Index: 891693 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7077. Min Act: -0.0000

Data Index: 857128 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6672. Min Act: -0.0000

Data Index: 153838 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1270615 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5741. Min Act: -0.0000

Data Index: 600734 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6571. Min Act: -0.0000

Data Index: 366943 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6958. Min Act: -0.0000

Data Index: 85617 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6321. Min Act: -0.0000

Data Index: 272603 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6256. Min Act: -0.0000

Data Index: 860710 (C4 (Web Text))

Max Activating Token Index: 599