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

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

Neuron 5250 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.3846. Min Act: -0.0001

Data Index: 1003342 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.1432. Min Act: -0.0001

Data Index: 209758 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0482. Min Act: -0.0000

Data Index: 784292 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1309934 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0665. Min Act: -0.0000

Data Index: 815366 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0678. Min Act: -0.0000

Data Index: 997839 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9360. Min Act: -0.0000

Data Index: 178093 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9228. Min Act: -0.0000

Data Index: 143580 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9669. Min Act: -0.0000

Data Index: 480521 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9343. Min Act: -0.0000

Data Index: 947084 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9550. Min Act: -0.0000

Data Index: 87080 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9064. Min Act: -0.0000

Data Index: 580294 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.8060. Min Act: -0.0000

Data Index: 844510 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9042. Min Act: -0.0001

Data Index: 1074682 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.8447. Min Act: -0.0000

Data Index: 143990 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.8826. Min Act: -0.0001

Data Index: 377214 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.8313. Min Act: -0.0001

Data Index: 123717 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1314902 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.8282. Min Act: -0.0000

Data Index: 228486 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.8219. Min Act: -0.0000

Data Index: 954994 (C4 (Web Text))

Max Activating Token Index: 332