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

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

Neuron 4905 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: 0.6048. Min Range: -0.6048

Max Act: 0.6048. Min Act: -0.0000

Data Index: 464320 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5517. Min Act: -0.0000

Data Index: 775016 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5305. Min Act: -0.0000

Data Index: 140381 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4900. Min Act: -0.0000

Data Index: 323225 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1066298 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1097130 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4321. Min Act: -0.0000

Data Index: 865227 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4130. Min Act: -0.0000

Data Index: 510592 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4122. Min Act: -0.0000

Data Index: 303961 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4110. Min Act: -0.0000

Data Index: 797756 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4007. Min Act: -0.0000

Data Index: 587840 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3986. Min Act: -0.0000

Data Index: 659144 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3911. Min Act: -0.0000

Data Index: 296263 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3866. Min Act: -0.0000

Data Index: 912228 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1326419 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1100592 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1225788 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1268785 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1292656 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3680. Min Act: -0.0000

Data Index: 573611 (C4 (Web Text))

Max Activating Token Index: 132