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

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

Neuron 4101 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.8751. Min Act: 0.0000

Data Index: 459466 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.8632. Min Act: -0.0000

Data Index: 965532 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.7065. Min Act: 0.0000

Data Index: 484728 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1118376 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6255. Min Act: -0.0000

Data Index: 352731 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5692. Min Act: 0.0000

Data Index: 146776 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5536. Min Act: -0.0000

Data Index: 164569 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1164937 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4863. Min Act: 0.0000

Data Index: 887071 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4938. Min Act: -0.0000

Data Index: 281609 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5018. Min Act: -0.0000

Data Index: 652047 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4289. Min Act: -0.0000

Data Index: 166717 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4295. Min Act: 0.0000

Data Index: 195414 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4219. Min Act: 0.0001

Data Index: 372962 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4335. Min Act: -0.0000

Data Index: 281930 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4056. Min Act: 0.0000

Data Index: 64148 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4145. Min Act: -0.0000

Data Index: 250052 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4153. Min Act: 0.0001

Data Index: 842011 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4241. Min Act: 0.0000

Data Index: 1305948 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1299903 (C4 (Web Text))

Max Activating Token Index: 520