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

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

Neuron 2063 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: 7.6162. Min Range: -7.6162

Max Act: 7.5639. Min Act: -0.0000

Data Index: 317196 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 7.6162. Min Range: -7.6162

Max Act: 7.6162. Min Act: -0.0000

Data Index: 283053 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 7.6162. Min Range: -7.6162

Max Act: 7.4252. Min Act: -0.0000

Data Index: 373893 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 7.6162. Min Range: -7.6162

Max Act: 6.7129. Min Act: -0.0000

Data Index: 1074735 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 7.6162. Min Range: -7.6162

Max Act: 7.1894. Min Act: -0.0000

Data Index: 759213 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 7.6162. Min Range: -7.6162

Max Act: 6.9743. Min Act: -0.0000

Data Index: 680652 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 7.6162. Min Range: -7.6162

Max Act: 6.6153. Min Act: -0.0000

Data Index: 711857 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 7.6162. Min Range: -7.6162

Max Act: 6.3110. Min Act: -0.0000

Data Index: 162592 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 7.6162. Min Range: -7.6162

Max Act: 5.9408. Min Act: -0.0000

Data Index: 653624 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 7.6162. Min Range: -7.6162

Max Act: 6.3027. Min Act: -0.0000

Data Index: 1026255 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 7.6162. Min Range: -7.6162

Max Act: 6.4230. Min Act: -0.0000

Data Index: 606395 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 7.6162. Min Range: -7.6162

Max Act: 6.2119. Min Act: -0.0000

Data Index: 382261 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 7.6162. Min Range: -7.6162

Max Act: 5.4732. Min Act: -0.0000

Data Index: 952202 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 7.6162. Min Range: -7.6162

Max Act: 5.6118. Min Act: -0.0000

Data Index: 48044 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 7.6162. Min Range: -7.6162

Max Act: 5.3300. Min Act: -0.0000

Data Index: 3923 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 7.6162. Min Range: -7.6162

Max Act: 4.7445. Min Act: -0.0000

Data Index: 1000784 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 7.6162. Min Range: -7.6162

Max Act: 4.2401. Min Act: -0.0000

Data Index: 389896 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 7.6162. Min Range: -7.6162

Max Act: 3.6146. Min Act: -0.0000

Data Index: 348700 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 7.6162. Min Range: -7.6162

Max Act: 2.8460. Min Act: -0.0000

Data Index: 1348247 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 7.6162. Min Range: -7.6162

Max Act: 2.8015. Min Act: -0.0000

Data Index: 1197580 (C4 (Web Text))

Max Activating Token Index: 954