Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.4279. Min Act: -0.0001

Data Index: 475290 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1348743 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3550. Min Act: -0.0001

Data Index: 426644 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3423. Min Act: -0.0001

Data Index: 659812 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1279344 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3428. Min Act: -0.0001

Data Index: 654413 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3308. Min Act: -0.0001

Data Index: 175080 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3187. Min Act: -0.0001

Data Index: 736906 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3362. Min Act: -0.0001

Data Index: 379932 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3052. Min Act: -0.0001

Data Index: 468148 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2927. Min Act: -0.0001

Data Index: 270994 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3027. Min Act: -0.0001

Data Index: 722641 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2886. Min Act: -0.0001

Data Index: 469662 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2731. Min Act: -0.0001

Data Index: 376360 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2849. Min Act: -0.0001

Data Index: 672913 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2811. Min Act: -0.0001

Data Index: 769475 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2840. Min Act: -0.0001

Data Index: 669293 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2925. Min Act: -0.0001

Data Index: 178084 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2903. Min Act: -0.0001

Data Index: 427990 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2810. Min Act: -0.0001

Data Index: 964432 (C4 (Web Text))

Max Activating Token Index: 40