Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3117 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2635. Min Range: -1.2635

Max Act: 1.2635. Min Act: -0.0000

Data Index: 581634 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 1.2635. Min Range: -1.2635

Max Act: 1.1423. Min Act: -0.0000

Data Index: 273713 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1039582 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9554. Min Act: -0.0000

Data Index: 344279 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9544. Min Act: -0.0000

Data Index: 125486 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1067475 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1230638 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1015997 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9303. Min Act: -0.0000

Data Index: 539 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9118. Min Act: -0.0000

Data Index: 991670 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9373. Min Act: -0.0000

Data Index: 59703 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8725. Min Act: -0.0000

Data Index: 944856 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9110. Min Act: -0.0000

Data Index: 953840 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1201236 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8437. Min Act: -0.0000

Data Index: 294613 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8405. Min Act: -0.0000

Data Index: 499552 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1184485 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8170. Min Act: -0.0000

Data Index: 926015 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1098385 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1245110 (C4 (Web Text))

Max Activating Token Index: 731