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

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

Neuron 565 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0001

Data Index: 145939 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0428. Min Act: -0.0001

Data Index: 81450 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0457. Min Act: -0.0001

Data Index: 146746 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0425. Min Act: -0.0001

Data Index: 676493 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0428. Min Act: -0.0001

Data Index: 628943 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0404. Min Act: -0.0001

Data Index: 952234 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0405. Min Act: -0.0001

Data Index: 858987 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0390. Min Act: -0.0001

Data Index: 323203 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1339744 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0406. Min Act: -0.0001

Data Index: 813165 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1318166 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0413. Min Act: -0.0001

Data Index: 534770 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0384. Min Act: -0.0001

Data Index: 304075 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0368. Min Act: -0.0001

Data Index: 406313 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0369. Min Act: -0.0001

Data Index: 847069 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0368. Min Act: -0.0001

Data Index: 77773 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0366. Min Act: -0.0001

Data Index: 898121 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0366. Min Act: -0.0001

Data Index: 209613 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0344. Min Act: -0.0001

Data Index: 990600 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0345. Min Act: -0.0001

Data Index: 234525 (C4 (Web Text))

Max Activating Token Index: 493