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

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

Neuron 1917 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: 4.0071. Min Range: -4.0071

Max Act: 4.0071. Min Act: -0.0000

Data Index: 303048 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.9591. Min Act: -0.0000

Data Index: 1222761 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.7897. Min Act: -0.0000

Data Index: 306023 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.9714. Min Act: -0.0000

Data Index: 1102823 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.8286. Min Act: -0.0000

Data Index: 386964 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.7971. Min Act: -0.0000

Data Index: 1143140 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.8980. Min Act: -0.0000

Data Index: 852524 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.5235. Min Act: -0.0000

Data Index: 426526 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.6446. Min Act: -0.0000

Data Index: 692503 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.4749. Min Act: -0.0000

Data Index: 472888 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.7540. Min Act: -0.0000

Data Index: 512287 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.5757. Min Act: -0.0000

Data Index: 1244276 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.5721. Min Act: -0.0000

Data Index: 1259133 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.5484. Min Act: -0.0000

Data Index: 671330 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.4073. Min Act: -0.0000

Data Index: 558067 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.6944. Min Act: -0.0000

Data Index: 378438 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.4006. Min Act: -0.0000

Data Index: 1005858 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.5300. Min Act: -0.0000

Data Index: 117038 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.3549. Min Act: -0.0000

Data Index: 651022 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 4.0071. Min Range: -4.0071

Max Act: 3.3568. Min Act: -0.0000

Data Index: 948368 (C4 (Web Text))

Max Activating Token Index: 951