Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1316 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1204. Min Act: -0.0004

Data Index: 814882 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0004

Data Index: 523819 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1096. Min Act: -0.0004

Data Index: 1339596 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1082. Min Act: -0.0004

Data Index: 1081193 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1035. Min Act: -0.0004

Data Index: 717443 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0929. Min Act: -0.0004

Data Index: 692083 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0891. Min Act: -0.0004

Data Index: 94180 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0927. Min Act: -0.0004

Data Index: 6520 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0905. Min Act: -0.0004

Data Index: 874070 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0899. Min Act: -0.0004

Data Index: 338545 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0901. Min Act: -0.0004

Data Index: 625401 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0897. Min Act: -0.0004

Data Index: 902692 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0847. Min Act: -0.0004

Data Index: 807992 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0874. Min Act: -0.0004

Data Index: 1071859 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0831. Min Act: -0.0004

Data Index: 298119 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0832. Min Act: -0.0004

Data Index: 477861 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0800. Min Act: -0.0004

Data Index: 843648 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0825. Min Act: -0.0004

Data Index: 805045 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0856. Min Act: -0.0004

Data Index: 450662 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0821. Min Act: -0.0004

Data Index: 599692 (C4 (Web Text))

Max Activating Token Index: 144