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

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

Neuron 771 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.6124. Min Act: -0.0001

Data Index: 1490691 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5148. Min Act: -0.0001

Data Index: 619209 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5420. Min Act: -0.0001

Data Index: 1027956 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5322. Min Act: -0.0001

Data Index: 714522 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5104. Min Act: -0.0001

Data Index: 28106 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1438126 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5305. Min Act: -0.0001

Data Index: 1559836 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5312. Min Act: -0.0001

Data Index: 1604368 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5102. Min Act: -0.0001

Data Index: 642102 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5017. Min Act: -0.0001

Data Index: 221436 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4992. Min Act: -0.0001

Data Index: 100154 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4970. Min Act: -0.0001

Data Index: 354916 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4981. Min Act: -0.0001

Data Index: 628031 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4765. Min Act: -0.0001

Data Index: 351460 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4893. Min Act: -0.0001

Data Index: 445376 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4909. Min Act: -0.0001

Data Index: 771811 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.5255. Min Act: -0.0001

Data Index: 399588 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4852. Min Act: -0.0001

Data Index: 1227581 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1211448 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.6124. Min Range: -0.6124

Max Act: 0.4684. Min Act: -0.0001

Data Index: 491106 (C4 (Web Text))

Max Activating Token Index: 513