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

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

Neuron 2995 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1035873 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1068355 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8122. Min Act: -0.0001

Data Index: 700545 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8117. Min Act: -0.0001

Data Index: 1010588 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7048. Min Act: -0.0001

Data Index: 262465 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7005. Min Act: -0.0001

Data Index: 634312 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7031. Min Act: -0.0001

Data Index: 166653 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1030364 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6899. Min Act: -0.0001

Data Index: 1037018 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6699. Min Act: -0.0001

Data Index: 381613 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6461. Min Act: -0.0001

Data Index: 1277190 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7542. Min Act: -0.0001

Data Index: 1124075 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.5968. Min Act: -0.0001

Data Index: 1635740 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6280. Min Act: -0.0001

Data Index: 982604 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6442. Min Act: -0.0001

Data Index: 1014790 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.5840. Min Act: -0.0001

Data Index: 1505116 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6028. Min Act: -0.0001

Data Index: 1027807 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.5744. Min Act: -0.0001

Data Index: 576353 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6412. Min Act: -0.0001

Data Index: 12125 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.5196. Min Act: -0.0001

Data Index: 848407 (C4 (Web Text))

Max Activating Token Index: 153