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

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

Neuron 976 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2840. Min Range: -4.2840

Max Act: 4.2840. Min Act: -0.0000

Data Index: 324307 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.8993. Min Act: -0.0000

Data Index: 12056 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.4618. Min Act: -0.0000

Data Index: 1355320 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.5231. Min Act: -0.0000

Data Index: 1195223 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.4027. Min Act: -0.0000

Data Index: 274173 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.3190. Min Act: -0.0000

Data Index: 104095 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.3140. Min Act: -0.0000

Data Index: 1231249 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.3007. Min Act: -0.0000

Data Index: 529054 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.3141. Min Act: -0.0000

Data Index: 1231243 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.1300. Min Act: -0.0000

Data Index: 900350 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.2778. Min Act: -0.0000

Data Index: 1285767 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.0105. Min Act: -0.0000

Data Index: 75321 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 4.2840. Min Range: -4.2840

Max Act: 2.9699. Min Act: -0.0000

Data Index: 216259 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 4.2840. Min Range: -4.2840

Max Act: 2.7744. Min Act: -0.0000

Data Index: 552576 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.0620. Min Act: -0.0000

Data Index: 1350856 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 4.2840. Min Range: -4.2840

Max Act: 2.8758. Min Act: -0.0000

Data Index: 959072 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 4.2840. Min Range: -4.2840

Max Act: 2.7007. Min Act: -0.0000

Data Index: 97486 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 4.2840. Min Range: -4.2840

Max Act: 2.7620. Min Act: -0.0000

Data Index: 68054 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 4.2840. Min Range: -4.2840

Max Act: 2.7418. Min Act: -0.0000

Data Index: 167113 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 4.2840. Min Range: -4.2840

Max Act: 2.6087. Min Act: -0.0000

Data Index: 628248 (C4 (Web Text))

Max Activating Token Index: 342