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

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

Neuron 3539 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1076082 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.0209. Min Act: -0.0000

Data Index: 468520 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9521. Min Act: -0.0000

Data Index: 589878 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1059481 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9090. Min Act: -0.0000

Data Index: 53522 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1039561 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8858. Min Act: -0.0000

Data Index: 801934 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1132557 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8685. Min Act: 0.0000

Data Index: 1249163 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1078860 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8100. Min Act: -0.0000

Data Index: 12525 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8664. Min Act: -0.0000

Data Index: 94227 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8367. Min Act: -0.0000

Data Index: 775129 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8040. Min Act: -0.0000

Data Index: 883256 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8175. Min Act: -0.0000

Data Index: 447255 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1343031 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.7899. Min Act: 0.0000

Data Index: 120844 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.7904. Min Act: -0.0000

Data Index: 85869 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.8153. Min Act: 0.0000

Data Index: 817409 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1188919 (C4 (Web Text))

Max Activating Token Index: 453