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

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

Neuron 4188 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.5621. Min Act: -0.0000

Data Index: 919973 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.2725. Min Act: -0.0000

Data Index: 1164953 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.4876. Min Act: -0.0000

Data Index: 164504 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.4109. Min Act: -0.0000

Data Index: 501187 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.5071. Min Act: -0.0000

Data Index: 141262 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.2164. Min Act: -0.0000

Data Index: 3987 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.2241. Min Act: -0.0000

Data Index: 962569 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 2.5621. Min Range: -2.5621

Max Act: 1.9951. Min Act: -0.0000

Data Index: 781279 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.2151. Min Act: -0.0000

Data Index: 105117 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.0987. Min Act: -0.0000

Data Index: 287276 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.4294. Min Act: -0.0000

Data Index: 1358042 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.1908. Min Act: -0.0001

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.1552. Min Act: -0.0000

Data Index: 892017 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.2847. Min Act: -0.0000

Data Index: 1046159 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.0312. Min Act: -0.0000

Data Index: 191582 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.2133. Min Act: -0.0001

Data Index: 956614 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.1028. Min Act: -0.0000

Data Index: 440900 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 2.5621. Min Range: -2.5621

Max Act: 1.8936. Min Act: -0.0001

Data Index: 1007805 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 2.5621. Min Range: -2.5621

Max Act: 2.0702. Min Act: -0.0000

Data Index: 1074154 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 2.5621. Min Range: -2.5621

Max Act: 1.9604. Min Act: -0.0000

Data Index: 794790 (C4 (Web Text))

Max Activating Token Index: 372