Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3986 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5886. Min Act: -0.0003

Data Index: 1186872 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5747. Min Act: -0.0002

Data Index: 983021 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5614. Min Act: -0.0003

Data Index: 826253 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5532. Min Act: -0.0003

Data Index: 955807 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5420. Min Act: -0.0003

Data Index: 422447 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5585. Min Act: -0.0002

Data Index: 496713 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5300. Min Act: -0.0003

Data Index: 359130 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5175. Min Act: -0.0003

Data Index: 171027 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5142. Min Act: -0.0003

Data Index: 1035577 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4844. Min Act: -0.0003

Data Index: 1072532 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4682. Min Act: -0.0003

Data Index: 795181 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4825. Min Act: -0.0003

Data Index: 857595 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4599. Min Act: -0.0003

Data Index: 786017 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4592. Min Act: -0.0002

Data Index: 101766 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4549. Min Act: -0.0003

Data Index: 952562 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4253. Min Act: -0.0003

Data Index: 99132 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4230. Min Act: -0.0002

Data Index: 739972 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4190. Min Act: -0.0003

Data Index: 728405 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4300. Min Act: -0.0003

Data Index: 990920 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4116. Min Act: -0.0003

Data Index: 452716 (C4 (Web Text))

Max Activating Token Index: 359