Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1162151 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1137144 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1073128 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5259. Min Act: -0.0000

Data Index: 267927 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5110. Min Act: -0.0000

Data Index: 708643 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4942. Min Act: -0.0000

Data Index: 982962 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4891. Min Act: -0.0001

Data Index: 1226857 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4854. Min Act: -0.0001

Data Index: 451688 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1214870 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4755. Min Act: -0.0000

Data Index: 279140 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4745. Min Act: -0.0000

Data Index: 724724 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4843. Min Act: -0.0001

Data Index: 1319000 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1057016 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4491. Min Act: -0.0001

Data Index: 48884 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4346. Min Act: -0.0000

Data Index: 713899 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4165. Min Act: -0.0000

Data Index: 681785 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4273. Min Act: -0.0001

Data Index: 635066 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1170553 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4166. Min Act: -0.0000

Data Index: 656662 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4124. Min Act: -0.0000

Data Index: 534331 (C4 (Web Text))

Max Activating Token Index: 220