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

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

Neuron 1473 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.5713. Min Act: -0.0002

Data Index: 761403 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3165. Min Act: -0.0002

Data Index: 390535 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2444. Min Act: -0.0002

Data Index: 8474 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3080. Min Act: -0.0002

Data Index: 1132426 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3166. Min Act: -0.0002

Data Index: 799964 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2728. Min Act: -0.0002

Data Index: 321043 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.3449. Min Act: -0.0002

Data Index: 1356008 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2546. Min Act: -0.0002

Data Index: 108070 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2078. Min Act: -0.0002

Data Index: 1146717 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.1064. Min Act: -0.0002

Data Index: 469183 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2241. Min Act: -0.0002

Data Index: 956818 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2280. Min Act: -0.0002

Data Index: 1188995 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.1119. Min Act: -0.0002

Data Index: 661278 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.1954. Min Act: -0.0002

Data Index: 847338 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.1900. Min Act: -0.0002

Data Index: 355538 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2546. Min Act: -0.0002

Data Index: 8844 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2177. Min Act: -0.0002

Data Index: 621249 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.1842. Min Act: -0.0002

Data Index: 1350353 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.2178. Min Act: -0.0002

Data Index: 894522 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.1446. Min Act: -0.0002

Data Index: 528487 (C4 (Web Text))

Max Activating Token Index: 11