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

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

Neuron 3281 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1532. Min Range: -1.1532

Max Act: 1.1532. Min Act: -0.0001

Data Index: 380956 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 1.1532. Min Range: -1.1532

Max Act: 1.0371. Min Act: -0.0001

Data Index: 1049330 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9060. Min Act: -0.0001

Data Index: 785916 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9274. Min Act: -0.0001

Data Index: 452301 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9353. Min Act: -0.0001

Data Index: 804017 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9401. Min Act: -0.0001

Data Index: 644192 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9946. Min Act: -0.0001

Data Index: 1058714 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9069. Min Act: -0.0001

Data Index: 236399 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9114. Min Act: -0.0001

Data Index: 1240115 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8868. Min Act: -0.0001

Data Index: 778845 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8506. Min Act: -0.0001

Data Index: 95945 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8271. Min Act: -0.0001

Data Index: 461808 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9016. Min Act: -0.0001

Data Index: 954707 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8937. Min Act: -0.0001

Data Index: 1354579 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8600. Min Act: -0.0001

Data Index: 842056 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8778. Min Act: -0.0001

Data Index: 683768 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.9015. Min Act: -0.0001

Data Index: 1137023 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8436. Min Act: -0.0001

Data Index: 715805 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8454. Min Act: -0.0001

Data Index: 464910 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.1532. Min Range: -1.1532

Max Act: 0.8152. Min Act: -0.0001

Data Index: 175973 (C4 (Web Text))

Max Activating Token Index: 494