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

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

Neuron 6096 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0002

Data Index: 113677 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1050161 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1011. Min Act: -0.0002

Data Index: 770367 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0907. Min Act: -0.0002

Data Index: 629586 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0922. Min Act: -0.0002

Data Index: 845068 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0835. Min Act: -0.0002

Data Index: 88338 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0861. Min Act: -0.0002

Data Index: 833529 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0887. Min Act: -0.0002

Data Index: 842446 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0848. Min Act: -0.0002

Data Index: 102593 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0845. Min Act: -0.0002

Data Index: 356480 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0809. Min Act: -0.0002

Data Index: 514682 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1190069 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0802. Min Act: -0.0002

Data Index: 268479 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0826. Min Act: -0.0002

Data Index: 585978 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0823. Min Act: -0.0002

Data Index: 262056 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0819. Min Act: -0.0002

Data Index: 432239 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1138941 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0816. Min Act: -0.0002

Data Index: 803821 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0807. Min Act: -0.0002

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1137216 (C4 (Web Text))

Max Activating Token Index: 122