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

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

Neuron 4661 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.2928. Min Act: -0.0000

Data Index: 194901 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.1314. Min Act: -0.0000

Data Index: 829857 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.0560. Min Act: -0.0000

Data Index: 509616 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1194559 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.0140. Min Act: -0.0000

Data Index: 439713 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.0753. Min Act: -0.0000

Data Index: 907634 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.9775. Min Act: -0.0000

Data Index: 979209 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8878. Min Act: -0.0000

Data Index: 223225 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.9202. Min Act: -0.0000

Data Index: 176164 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8638. Min Act: -0.0000

Data Index: 174598 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8960. Min Act: -0.0000

Data Index: 27877 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.9182. Min Act: -0.0000

Data Index: 142286 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1191009 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1343286 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8167. Min Act: -0.0000

Data Index: 392731 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8559. Min Act: 0.0000

Data Index: 840853 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7980. Min Act: -0.0000

Data Index: 735550 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7825. Min Act: -0.0000

Data Index: 116821 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7794. Min Act: -0.0000

Data Index: 58111 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7241. Min Act: -0.0000

Data Index: 266673 (C4 (Web Text))

Max Activating Token Index: 368