Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1661 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6058. Min Range: -2.6058

Max Act: 2.6058. Min Act: -0.0000

Data Index: 1047047 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 2.6058. Min Range: -2.6058

Max Act: 2.2886. Min Act: -0.0000

Data Index: 1143447 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 2.6058. Min Range: -2.6058

Max Act: 2.0572. Min Act: -0.0000

Data Index: 50304 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.9662. Min Act: -0.0000

Data Index: 864258 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.8619. Min Act: -0.0000

Data Index: 921917 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.9584. Min Act: -0.0000

Data Index: 815757 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.8622. Min Act: -0.0000

Data Index: 1099213 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.7845. Min Act: -0.0000

Data Index: 674675 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.7628. Min Act: -0.0000

Data Index: 154963 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.7342. Min Act: -0.0000

Data Index: 557119 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.7244. Min Act: -0.0000

Data Index: 125591 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.7100. Min Act: -0.0000

Data Index: 465095 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.7334. Min Act: -0.0000

Data Index: 630234 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.5406. Min Act: -0.0000

Data Index: 1211618 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.4039. Min Act: -0.0000

Data Index: 165688 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.5731. Min Act: -0.0000

Data Index: 251532 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.7293. Min Act: -0.0000

Data Index: 480220 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.6383. Min Act: -0.0000

Data Index: 518984 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.5384. Min Act: -0.0000

Data Index: 49529 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 2.6058. Min Range: -2.6058

Max Act: 1.6069. Min Act: -0.0000

Data Index: 625476 (C4 (Web Text))

Max Activating Token Index: 925