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

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

Neuron 769 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: 1.6124. Min Range: -1.6124

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1048152 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.3472. Min Act: -0.0000

Data Index: 480396 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2915. Min Act: -0.0000

Data Index: 101138 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1349011 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1025360 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1295664 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2344. Min Act: -0.0000

Data Index: 11277 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.3394. Min Act: -0.0000

Data Index: 993238 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2805. Min Act: -0.0000

Data Index: 836054 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2087. Min Act: -0.0000

Data Index: 602312 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2685. Min Act: -0.0000

Data Index: 382003 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2945. Min Act: -0.0000

Data Index: 1149649 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2668. Min Act: -0.0000

Data Index: 232675 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1201372 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2829. Min Act: -0.0000

Data Index: 380072 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2395. Min Act: -0.0000

Data Index: 859216 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2782. Min Act: -0.0000

Data Index: 138028 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2340. Min Act: -0.0000

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1149372 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 1.6124. Min Range: -1.6124

Max Act: 1.1871. Min Act: -0.0000

Data Index: 872958 (C4 (Web Text))

Max Activating Token Index: 840