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

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

Neuron 6104 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.7007. Min Act: -0.0000

Data Index: 1216223 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.5357. Min Act: -0.0000

Data Index: 173821 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.4125. Min Act: -0.0000

Data Index: 432363 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.0930. Min Act: -0.0000

Data Index: 212445 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.1454. Min Act: -0.0000

Data Index: 229457 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.2815. Min Act: -0.0000

Data Index: 797598 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.2316. Min Act: -0.0000

Data Index: 778138 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.1090. Min Act: -0.0000

Data Index: 1348289 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1276024 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.1717. Min Act: -0.0000

Data Index: 841473 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 2.7007. Min Range: -2.7007

Max Act: 2.1220. Min Act: -0.0000

Data Index: 1143393 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.8957. Min Act: -0.0000

Data Index: 583013 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.9393. Min Act: -0.0000

Data Index: 1252706 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.7918. Min Act: -0.0000

Data Index: 852296 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.8501. Min Act: -0.0000

Data Index: 62493 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.7954. Min Act: -0.0000

Data Index: 688820 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.8249. Min Act: -0.0000

Data Index: 672432 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.5054. Min Act: -0.0000

Data Index: 726520 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1039153 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 2.7007. Min Range: -2.7007

Max Act: 1.6755. Min Act: -0.0000

Data Index: 129895 (C4 (Web Text))

Max Activating Token Index: 826