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

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

Neuron 3178 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6114. Min Range: -4.6114

Max Act: 4.6114. Min Act: -0.0000

Data Index: 745829 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 4.6114. Min Range: -4.6114

Max Act: 3.8923. Min Act: -0.0000

Data Index: 1007161 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 4.6114. Min Range: -4.6114

Max Act: 3.4710. Min Act: -0.0000

Data Index: 1019419 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 4.6114. Min Range: -4.6114

Max Act: 3.0743. Min Act: -0.0000

Data Index: 158461 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 4.6114. Min Range: -4.6114

Max Act: 3.0127. Min Act: -0.0000

Data Index: 939149 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 4.6114. Min Range: -4.6114

Max Act: 3.0553. Min Act: -0.0000

Data Index: 952177 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.8866. Min Act: -0.0000

Data Index: 665017 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.7869. Min Act: -0.0000

Data Index: 1324201 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.7786. Min Act: -0.0000

Data Index: 525449 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.7331. Min Act: -0.0000

Data Index: 1209798 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.8034. Min Act: -0.0000

Data Index: 630205 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.5589. Min Act: -0.0000

Data Index: 304127 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.8341. Min Act: -0.0000

Data Index: 1099274 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.3765. Min Act: -0.0000

Data Index: 7287 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.8947. Min Act: -0.0000

Data Index: 505757 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.4433. Min Act: -0.0000

Data Index: 85672 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.5360. Min Act: -0.0000

Data Index: 769651 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.6696. Min Act: -0.0000

Data Index: 727426 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.4688. Min Act: -0.0000

Data Index: 345767 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 4.6114. Min Range: -4.6114

Max Act: 2.4647. Min Act: -0.0000

Data Index: 380917 (C4 (Web Text))

Max Activating Token Index: 105