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

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

Neuron 5058 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8903. Min Range: -7.8903

Max Act: 7.8903. Min Act: -0.0000

Data Index: 1049030 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 7.8903. Min Range: -7.8903

Max Act: 7.2026. Min Act: -0.0000

Data Index: 189082 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 7.8903. Min Range: -7.8903

Max Act: 6.1770. Min Act: -0.0000

Data Index: 1126098 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 7.8903. Min Range: -7.8903

Max Act: 5.8236. Min Act: -0.0000

Data Index: 906383 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 7.8903. Min Range: -7.8903

Max Act: 5.3839. Min Act: -0.0000

Data Index: 1091451 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.6227. Min Act: -0.0000

Data Index: 1229993 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.6034. Min Act: -0.0000

Data Index: 716484 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.5836. Min Act: -0.0000

Data Index: 533506 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.3672. Min Act: -0.0000

Data Index: 562158 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.2136. Min Act: -0.0000

Data Index: 1133905 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.3286. Min Act: -0.0000

Data Index: 17115 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.1105. Min Act: -0.0000

Data Index: 714237 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.3589. Min Act: -0.0000

Data Index: 348735 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 7.8903. Min Range: -7.8903

Max Act: 3.9969. Min Act: -0.0000

Data Index: 762966 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.2910. Min Act: -0.0000

Data Index: 431672 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.1125. Min Act: -0.0000

Data Index: 650713 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 7.8903. Min Range: -7.8903

Max Act: 3.9316. Min Act: -0.0000

Data Index: 695482 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 7.8903. Min Range: -7.8903

Max Act: 3.5736. Min Act: -0.0000

Data Index: 1125500 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 7.8903. Min Range: -7.8903

Max Act: 4.0144. Min Act: -0.0000

Data Index: 262752 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 7.8903. Min Range: -7.8903

Max Act: 3.7090. Min Act: -0.0000

Data Index: 591459 (C4 (Web Text))

Max Activating Token Index: 93