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

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

Neuron 4852 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6868. Min Range: -4.6868

Max Act: 4.6868. Min Act: -0.0000

Data Index: 489259 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 4.6868. Min Range: -4.6868

Max Act: 3.0994. Min Act: -0.0000

Data Index: 115716 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.8393. Min Act: -0.0000

Data Index: 555844 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.8032. Min Act: -0.0000

Data Index: 813089 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.6177. Min Act: -0.0000

Data Index: 967006 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.7016. Min Act: -0.0000

Data Index: 902791 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.8217. Min Act: -0.0000

Data Index: 1263791 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.6702. Min Act: -0.0000

Data Index: 668299 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.6569. Min Act: -0.0000

Data Index: 964862 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.6911. Min Act: -0.0000

Data Index: 186005 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.6764. Min Act: -0.0000

Data Index: 500077 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.7647. Min Act: -0.0000

Data Index: 380811 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.5715. Min Act: -0.0000

Data Index: 505413 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.5127. Min Act: -0.0000

Data Index: 730686 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.3013. Min Act: -0.0000

Data Index: 526663 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.4212. Min Act: -0.0000

Data Index: 272476 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.5459. Min Act: -0.0000

Data Index: 551896 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.5171. Min Act: -0.0000

Data Index: 1249546 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.4692. Min Act: -0.0000

Data Index: 271947 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 4.6868. Min Range: -4.6868

Max Act: 2.4748. Min Act: -0.0000

Data Index: 314836 (C4 (Web Text))

Max Activating Token Index: 676