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

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

Neuron 3746 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: 0.8982. Min Range: -0.8982

Max Act: 0.8982. Min Act: -0.0000

Data Index: 724981 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.8331. Min Act: -0.0000

Data Index: 109385 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.8369. Min Act: -0.0000

Data Index: 150969 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7799. Min Act: -0.0001

Data Index: 1038920 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1028630 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7372. Min Act: -0.0000

Data Index: 802294 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7223. Min Act: -0.0000

Data Index: 654300 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1208275 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6916. Min Act: -0.0001

Data Index: 214779 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7380. Min Act: -0.0000

Data Index: 525083 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1028893 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6726. Min Act: -0.0000

Data Index: 936984 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6900. Min Act: -0.0000

Data Index: 8133 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6607. Min Act: -0.0001

Data Index: 46020 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6589. Min Act: -0.0000

Data Index: 440023 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6748. Min Act: -0.0001

Data Index: 337192 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6742. Min Act: -0.0000

Data Index: 489577 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6742. Min Act: -0.0000

Data Index: 531370 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6724. Min Act: -0.0000

Data Index: 5204 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.8982. Min Range: -0.8982

Max Act: 0.6925. Min Act: -0.0001

Data Index: 839321 (C4 (Web Text))

Max Activating Token Index: 942