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

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

Neuron 4051 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: 1.1183. Min Range: -1.1183

Max Act: 1.1183. Min Act: -0.0000

Data Index: 303085 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1065034 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.9614. Min Act: -0.0000

Data Index: 393777 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.9423. Min Act: -0.0000

Data Index: 449842 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.9016. Min Act: -0.0000

Data Index: 88205 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8757. Min Act: -0.0000

Data Index: 743698 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8919. Min Act: -0.0000

Data Index: 585114 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1245922 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8769. Min Act: -0.0000

Data Index: 529087 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1240379 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8402. Min Act: -0.0000

Data Index: 373963 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8424. Min Act: -0.0000

Data Index: 175527 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8142. Min Act: -0.0000

Data Index: 543343 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8410. Min Act: -0.0000

Data Index: 793780 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1354956 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.7842. Min Act: -0.0000

Data Index: 791611 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8639. Min Act: -0.0000

Data Index: 272366 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8078. Min Act: -0.0000

Data Index: 880803 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1332713 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 1.1183. Min Range: -1.1183

Max Act: 0.8423. Min Act: -0.0000

Data Index: 747272 (C4 (Web Text))

Max Activating Token Index: 905