Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0886. Min Act: -0.0003

Data Index: 354001 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1031. Min Act: -0.0003

Data Index: 188417 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0977. Min Act: -0.0003

Data Index: 91787 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0897. Min Act: -0.0003

Data Index: 87122 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0918. Min Act: -0.0003

Data Index: 507777 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1191483 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0981. Min Act: -0.0003

Data Index: 1060193 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0875. Min Act: -0.0003

Data Index: 544578 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0821. Min Act: -0.0003

Data Index: 604983 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0833. Min Act: -0.0003

Data Index: 1304458 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0947. Min Act: -0.0003

Data Index: 921289 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0885. Min Act: -0.0003

Data Index: 44761 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0975. Min Act: -0.0003

Data Index: 435631 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0847. Min Act: -0.0003

Data Index: 114956 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0877. Min Act: -0.0003

Data Index: 688350 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0837. Min Act: -0.0003

Data Index: 350733 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0931. Min Act: -0.0003

Data Index: 25862 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0997. Min Act: -0.0003

Data Index: 612129 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0858. Min Act: -0.0003

Data Index: 796867 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0880. Min Act: -0.0003

Data Index: 595855 (C4 (Web Text))

Max Activating Token Index: 674