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

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

Neuron 1054 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.1107. Min Act: -0.0000

Data Index: 901719 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1345594 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0875. Min Act: -0.0000

Data Index: 99952 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1086135 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0897. Min Act: -0.0000

Data Index: 710485 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0818. Min Act: -0.0000

Data Index: 356381 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1113912 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0858. Min Act: -0.0001

Data Index: 50928 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0872. Min Act: -0.0000

Data Index: 259821 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0803. Min Act: -0.0000

Data Index: 281186 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0807. Min Act: -0.0000

Data Index: 331833 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0833. Min Act: -0.0000

Data Index: 760826 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0771. Min Act: -0.0000

Data Index: 917510 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0863. Min Act: -0.0000

Data Index: 102010 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0821. Min Act: -0.0000

Data Index: 102008 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0763. Min Act: -0.0000

Data Index: 315568 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0794. Min Act: -0.0000

Data Index: 868883 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1237299 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1018733 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0758. Min Act: -0.0000

Data Index: 850170 (C4 (Web Text))

Max Activating Token Index: 806