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

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

Neuron 5982 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.8189. Min Act: -0.0000

Data Index: 500143 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.8906. Min Act: -0.0000

Data Index: 291101 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.6159. Min Act: -0.0000

Data Index: 350351 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.4991. Min Act: -0.0001

Data Index: 764401 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.3907. Min Act: -0.0000

Data Index: 213719 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.5075. Min Act: -0.0000

Data Index: 730408 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.4883. Min Act: -0.0001

Data Index: 1251518 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.5793. Min Act: -0.0001

Data Index: 522065 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.5130. Min Act: -0.0001

Data Index: 361828 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.3844. Min Act: -0.0000

Data Index: 378021 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.4169. Min Act: -0.0000

Data Index: 500961 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.3564. Min Act: -0.0000

Data Index: 824688 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.4327. Min Act: -0.0001

Data Index: 1006321 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1127818 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.3920. Min Act: -0.0000

Data Index: 890746 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.3152. Min Act: -0.0001

Data Index: 17624 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1077658 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.3706. Min Act: -0.0000

Data Index: 103462 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.2686. Min Act: -0.0001

Data Index: 1168802 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.8906. Min Range: -1.8906

Max Act: 1.1811. Min Act: -0.0001

Data Index: 775744 (C4 (Web Text))

Max Activating Token Index: 340