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

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

Neuron 622 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1105598 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7763. Min Act: -0.0000

Data Index: 158785 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7945. Min Act: -0.0000

Data Index: 799668 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6950. Min Act: -0.0000

Data Index: 623524 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5971. Min Act: -0.0000

Data Index: 64885 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1247492 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1115480 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6336. Min Act: -0.0000

Data Index: 545732 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5939. Min Act: -0.0000

Data Index: 44060 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5913. Min Act: -0.0000

Data Index: 292833 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5709. Min Act: -0.0000

Data Index: 758345 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6141. Min Act: 0.0000

Data Index: 1242860 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5815. Min Act: -0.0000

Data Index: 875260 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1064334 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5647. Min Act: -0.0000

Data Index: 336969 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5820. Min Act: -0.0000

Data Index: 284885 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1100186 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1128236 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5319. Min Act: -0.0000

Data Index: 340929 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5177. Min Act: -0.0000

Data Index: 749179 (C4 (Web Text))

Max Activating Token Index: 977