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

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

Neuron 175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.4077. Min Act: -0.0001

Data Index: 1292272 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.3397. Min Act: -0.0002

Data Index: 639087 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.4075. Min Act: -0.0001

Data Index: 908626 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.2510. Min Act: -0.0001

Data Index: 872518 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.6157. Min Act: -0.0001

Data Index: 135690 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.3214. Min Act: -0.0001

Data Index: 201185 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.3673. Min Act: -0.0001

Data Index: 281303 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.2756. Min Act: -0.0001

Data Index: 1088158 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.6157. Min Range: -1.6157

Max Act: 0.9662. Min Act: -0.0001

Data Index: 1248807 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.1802. Min Act: -0.0001

Data Index: 1242809 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.2032. Min Act: -0.0001

Data Index: 1005840 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.2797. Min Act: -0.0001

Data Index: 257346 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.1703. Min Act: -0.0001

Data Index: 234326 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.1922. Min Act: -0.0001

Data Index: 1163426 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.6157. Min Range: -1.6157

Max Act: 0.9537. Min Act: -0.0001

Data Index: 891514 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.0401. Min Act: -0.0001

Data Index: 490746 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.6157. Min Range: -1.6157

Max Act: 0.9652. Min Act: -0.0001

Data Index: 735017 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.2884. Min Act: -0.0001

Data Index: 364048 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.1606. Min Act: -0.0001

Data Index: 776932 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.6157. Min Range: -1.6157

Max Act: 1.2283. Min Act: -0.0001

Data Index: 324723 (C4 (Web Text))

Max Activating Token Index: 723