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

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

Neuron 546 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.9170. Min Act: -0.0000

Data Index: 165565 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.9201. Min Act: -0.0000

Data Index: 553176 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.5699. Min Act: -0.0000

Data Index: 1326600 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.5064. Min Act: -0.0000

Data Index: 469740 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.3739. Min Act: -0.0000

Data Index: 1053003 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.5898. Min Act: -0.0000

Data Index: 1221815 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.4466. Min Act: -0.0000

Data Index: 187854 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.5969. Min Act: -0.0000

Data Index: 647284 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.0937. Min Act: -0.0000

Data Index: 504453 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.2354. Min Act: -0.0000

Data Index: 598960 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.4911. Min Act: -0.0000

Data Index: 732331 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.2954. Min Act: -0.0001

Data Index: 921793 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.2880. Min Act: -0.0001

Data Index: 1069801 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.1678. Min Act: -0.0000

Data Index: 1017144 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.3879. Min Act: -0.0001

Data Index: 988290 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.3619. Min Act: -0.0000

Data Index: 887865 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.0021. Min Act: -0.0000

Data Index: 989237 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.1831. Min Act: -0.0001

Data Index: 559914 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.2752. Min Act: -0.0000

Data Index: 245037 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 2.9201. Min Range: -2.9201

Max Act: 2.2785. Min Act: -0.0000

Data Index: 1349914 (C4 (Web Text))

Max Activating Token Index: 687