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

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

Neuron 3737 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0003

Data Index: 777504 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0465. Min Act: -0.0003

Data Index: 293643 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0438. Min Act: -0.0003

Data Index: 891035 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0454. Min Act: -0.0003

Data Index: 274602 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1141250 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0433. Min Act: -0.0003

Data Index: 62892 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0422. Min Act: -0.0003

Data Index: 92635 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1202533 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0408. Min Act: -0.0003

Data Index: 68939 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1248916 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0379. Min Act: -0.0003

Data Index: 858417 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0396. Min Act: -0.0003

Data Index: 392733 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1289811 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0380. Min Act: -0.0003

Data Index: 767600 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0388. Min Act: -0.0003

Data Index: 138665 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1119559 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0366. Min Act: -0.0003

Data Index: 515875 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0364. Min Act: -0.0003

Data Index: 921130 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0372. Min Act: -0.0003

Data Index: 953993 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0388. Min Act: -0.0003

Data Index: 358697 (C4 (Web Text))

Max Activating Token Index: 822