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

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

Neuron 4982 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.6407. Min Act: -0.0000

Data Index: 799363 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5851. Min Act: -0.0000

Data Index: 41102 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5318. Min Act: -0.0000

Data Index: 491767 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5716. Min Act: -0.0000

Data Index: 523611 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5222. Min Act: -0.0000

Data Index: 329258 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5101. Min Act: -0.0000

Data Index: 47924 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1215796 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5187. Min Act: -0.0000

Data Index: 485222 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5199. Min Act: -0.0000

Data Index: 150957 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4774. Min Act: -0.0000

Data Index: 951766 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4928. Min Act: -0.0000

Data Index: 242890 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4900. Min Act: -0.0000

Data Index: 774846 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5014. Min Act: -0.0000

Data Index: 160184 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5009. Min Act: -0.0000

Data Index: 244439 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4501. Min Act: -0.0000

Data Index: 3461 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4787. Min Act: -0.0000

Data Index: 11821 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4573. Min Act: -0.0000

Data Index: 500739 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4693. Min Act: -0.0000

Data Index: 833318 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4706. Min Act: -0.0000

Data Index: 249301 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4544. Min Act: -0.0000

Data Index: 672663 (C4 (Web Text))

Max Activating Token Index: 377