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

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

Neuron 3112 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.6851. Min Act: -0.0000

Data Index: 462022 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.7021. Min Act: -0.0000

Data Index: 1192900 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.5647. Min Act: -0.0000

Data Index: 173156 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.8213. Min Act: -0.0000

Data Index: 671435 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.2192. Min Act: -0.0000

Data Index: 1034559 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.0324. Min Act: -0.0000

Data Index: 379757 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.9589. Min Act: -0.0000

Data Index: 1231912 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.8788. Min Act: -0.0000

Data Index: 244915 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.0690. Min Act: -0.0000

Data Index: 979069 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.0547. Min Act: -0.0000

Data Index: 954917 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.6708. Min Act: -0.0000

Data Index: 146225 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 4.8213. Min Range: -4.8213

Max Act: 4.1728. Min Act: -0.0000

Data Index: 1100151 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.8370. Min Act: -0.0000

Data Index: 1078545 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.6713. Min Act: -0.0000

Data Index: 90129 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.4916. Min Act: -0.0000

Data Index: 902307 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.7739. Min Act: -0.0000

Data Index: 561262 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.8475. Min Act: -0.0000

Data Index: 754035 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.6648. Min Act: -0.0000

Data Index: 1139631 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.6352. Min Act: -0.0000

Data Index: 241857 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 4.8213. Min Range: -4.8213

Max Act: 3.5511. Min Act: -0.0000

Data Index: 282874 (C4 (Web Text))

Max Activating Token Index: 167