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

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

Neuron 2957 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2239. Min Act: -0.0001

Data Index: 178898 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1612. Min Act: -0.0001

Data Index: 134651 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1144. Min Act: -0.0001

Data Index: 393988 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1130. Min Act: -0.0001

Data Index: 741337 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1178. Min Act: -0.0001

Data Index: 708876 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1236. Min Act: -0.0001

Data Index: 968412 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1202. Min Act: -0.0001

Data Index: 715746 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1111. Min Act: -0.0001

Data Index: 61817 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0984. Min Act: -0.0001

Data Index: 120293 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1078. Min Act: -0.0001

Data Index: 644303 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0866. Min Act: -0.0001

Data Index: 965084 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1017597 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1019. Min Act: -0.0001

Data Index: 43490 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0874. Min Act: -0.0001

Data Index: 411282 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1045. Min Act: -0.0001

Data Index: 885883 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0783. Min Act: -0.0001

Data Index: 677911 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0855. Min Act: -0.0001

Data Index: 556428 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1100304 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0839. Min Act: -0.0001

Data Index: 796209 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1042636 (C4 (Web Text))

Max Activating Token Index: 505