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

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

Neuron 3952 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: 0.5407. Min Range: -0.5407

Max Act: 0.5043. Min Act: -0.0001

Data Index: 317578 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.5012. Min Act: -0.0001

Data Index: 1223193 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.5407. Min Act: -0.0001

Data Index: 812408 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.5130. Min Act: -0.0001

Data Index: 204375 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1125142 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4880. Min Act: -0.0001

Data Index: 810823 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4997. Min Act: -0.0001

Data Index: 959965 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4628. Min Act: -0.0001

Data Index: 35739 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4765. Min Act: -0.0001

Data Index: 965367 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1032688 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4461. Min Act: -0.0001

Data Index: 453592 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4424. Min Act: -0.0001

Data Index: 349530 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4276. Min Act: -0.0001

Data Index: 944819 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4270. Min Act: -0.0001

Data Index: 399336 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4218. Min Act: -0.0001

Data Index: 794337 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4203. Min Act: -0.0001

Data Index: 987753 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4426. Min Act: -0.0001

Data Index: 244837 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4104. Min Act: -0.0001

Data Index: 1339386 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.4388. Min Act: -0.0001

Data Index: 706155 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.5407. Min Range: -0.5407

Max Act: 0.3913. Min Act: -0.0001

Data Index: 974082 (C4 (Web Text))

Max Activating Token Index: 235