Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4301 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.4718. Min Act: -0.0000

Data Index: 983566 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.4204. Min Act: -0.0000

Data Index: 394614 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.3635. Min Act: -0.0000

Data Index: 808613 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.2576. Min Act: -0.0000

Data Index: 439923 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.1388. Min Act: -0.0000

Data Index: 1006376 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.2694. Min Act: -0.0000

Data Index: 1001847 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.2496. Min Act: -0.0000

Data Index: 444730 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.2161. Min Act: -0.0000

Data Index: 1011767 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.2004. Min Act: -0.0000

Data Index: 990939 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.0286. Min Act: -0.0000

Data Index: 57603 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.1465. Min Act: -0.0000

Data Index: 16994 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.1128. Min Act: -0.0000

Data Index: 1079172 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.2124. Min Act: -0.0000

Data Index: 875686 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.1922. Min Act: -0.0000

Data Index: 1292436 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.0759. Min Act: -0.0000

Data Index: 683929 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.0835. Min Act: -0.0000

Data Index: 815330 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 2.4718. Min Range: -2.4718

Max Act: 1.9514. Min Act: -0.0000

Data Index: 504285 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.0119. Min Act: -0.0000

Data Index: 433748 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 2.4718. Min Range: -2.4718

Max Act: 2.0136. Min Act: -0.0000

Data Index: 640439 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 2.4718. Min Range: -2.4718

Max Act: 1.8914. Min Act: -0.0000

Data Index: 550204 (C4 (Web Text))

Max Activating Token Index: 954