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

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

Neuron 1992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.5060. Min Act: -0.0000

Data Index: 778601 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4984. Min Act: -0.0001

Data Index: 1086608 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4924. Min Act: -0.0000

Data Index: 421054 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4726. Min Act: -0.0000

Data Index: 109239 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4801. Min Act: -0.0000

Data Index: 499724 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4680. Min Act: -0.0000

Data Index: 469248 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4795. Min Act: -0.0001

Data Index: 121466 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1234836 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4651. Min Act: -0.0000

Data Index: 280691 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4449. Min Act: -0.0001

Data Index: 863883 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4609. Min Act: -0.0000

Data Index: 52356 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4605. Min Act: -0.0001

Data Index: 908965 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4475. Min Act: -0.0001

Data Index: 792616 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4417. Min Act: -0.0000

Data Index: 503983 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4574. Min Act: -0.0000

Data Index: 552909 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4559. Min Act: -0.0000

Data Index: 545213 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4379. Min Act: -0.0001

Data Index: 1604107 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4499. Min Act: -0.0001

Data Index: 1098512 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4476. Min Act: -0.0001

Data Index: 972172 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4457. Min Act: -0.0001

Data Index: 388266 (C4 (Web Text))

Max Activating Token Index: 73