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

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

Neuron 4268 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3838. Min Range: -2.3838

Max Act: 2.3838. Min Act: -0.0000

Data Index: 984415 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.3838. Min Range: -2.3838

Max Act: 2.0120. Min Act: -0.0000

Data Index: 493938 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.9737. Min Act: -0.0000

Data Index: 919309 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.9503. Min Act: -0.0000

Data Index: 547692 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.9250. Min Act: -0.0000

Data Index: 1133613 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.9095. Min Act: -0.0000

Data Index: 1183365 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.7758. Min Act: -0.0000

Data Index: 69563 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.7540. Min Act: -0.0000

Data Index: 834472 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.6502. Min Act: -0.0000

Data Index: 812734 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.6986. Min Act: -0.0000

Data Index: 1047314 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.7803. Min Act: 0.0000

Data Index: 830725 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.6622. Min Act: -0.0000

Data Index: 1159463 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.6047. Min Act: -0.0000

Data Index: 161042 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.4994. Min Act: -0.0000

Data Index: 361038 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.5719. Min Act: -0.0000

Data Index: 666784 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.4882. Min Act: -0.0000

Data Index: 605300 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.5493. Min Act: -0.0000

Data Index: 708846 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.5473. Min Act: -0.0000

Data Index: 1316571 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.5889. Min Act: -0.0000

Data Index: 863124 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 2.3838. Min Range: -2.3838

Max Act: 1.6252. Min Act: -0.0000

Data Index: 511721 (C4 (Web Text))

Max Activating Token Index: 92