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

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

Neuron 2870 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5892. Min Range: -2.5892

Max Act: 2.5892. Min Act: -0.0000

Data Index: 491217 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 2.5892. Min Range: -2.5892

Max Act: 2.5207. Min Act: -0.0000

Data Index: 767752 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.9073. Min Act: -0.0000

Data Index: 1281370 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.8827. Min Act: -0.0000

Data Index: 614562 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.7749. Min Act: -0.0000

Data Index: 921865 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.8175. Min Act: -0.0000

Data Index: 1037158 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.9034. Min Act: -0.0000

Data Index: 1073463 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.8765. Min Act: -0.0000

Data Index: 500340 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.8177. Min Act: -0.0000

Data Index: 434406 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.9124. Min Act: -0.0000

Data Index: 576729 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.5390. Min Act: -0.0000

Data Index: 20988 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1065887 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.4714. Min Act: -0.0000

Data Index: 179032 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1109042 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.5067. Min Act: -0.0000

Data Index: 785564 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.4235. Min Act: -0.0000

Data Index: 280038 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1035789 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1195657 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1339402 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 2.5892. Min Range: -2.5892

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1012135 (C4 (Web Text))

Max Activating Token Index: 844