Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1866 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0004

Data Index: 271304 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0962. Min Act: -0.0003

Data Index: 607157 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0936. Min Act: -0.0004

Data Index: 133448 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0885. Min Act: -0.0003

Data Index: 910398 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0882. Min Act: -0.0002

Data Index: 69963 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0886. Min Act: -0.0003

Data Index: 352920 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0883. Min Act: -0.0004

Data Index: 651178 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0873. Min Act: -0.0003

Data Index: 820813 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1005947 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0796. Min Act: -0.0003

Data Index: 426730 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0810. Min Act: -0.0003

Data Index: 876574 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0820. Min Act: -0.0003

Data Index: 114533 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0761. Min Act: -0.0003

Data Index: 200623 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0770. Min Act: -0.0003

Data Index: 142903 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0733. Min Act: -0.0004

Data Index: 1337111 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1294749 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0727. Min Act: -0.0003

Data Index: 908483 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0713. Min Act: -0.0003

Data Index: 121166 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0730. Min Act: -0.0004

Data Index: 673038 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0743. Min Act: -0.0003

Data Index: 473761 (C4 (Web Text))

Max Activating Token Index: 760