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

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

Neuron 3462 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: 3.1967. Min Range: -3.1967

Max Act: 3.1967. Min Act: -0.0000

Data Index: 346425 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.8113. Min Act: -0.0000

Data Index: 1057729 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.8722. Min Act: -0.0000

Data Index: 251085 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.7719. Min Act: -0.0000

Data Index: 129978 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.7578. Min Act: -0.0000

Data Index: 1198223 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.6190. Min Act: -0.0000

Data Index: 661311 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1265727 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.5802. Min Act: -0.0000

Data Index: 709259 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.4794. Min Act: -0.0000

Data Index: 257886 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.6164. Min Act: -0.0000

Data Index: 1116652 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.6626. Min Act: -0.0000

Data Index: 1288812 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.3857. Min Act: -0.0000

Data Index: 836949 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.4952. Min Act: -0.0000

Data Index: 1284243 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.2107. Min Act: -0.0000

Data Index: 841144 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.4491. Min Act: -0.0000

Data Index: 160106 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.3149. Min Act: -0.0000

Data Index: 1176390 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.4388. Min Act: -0.0000

Data Index: 600449 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.3122. Min Act: -0.0000

Data Index: 451241 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.4134. Min Act: -0.0000

Data Index: 123953 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.2983. Min Act: -0.0000

Data Index: 993127 (C4 (Web Text))

Max Activating Token Index: 888