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

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

Neuron 3898 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.8723. Min Act: -0.0001

Data Index: 546729 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.9879. Min Act: -0.0001

Data Index: 904335 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.9258. Min Act: -0.0001

Data Index: 570413 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.8999. Min Act: -0.0001

Data Index: 37467 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.3497. Min Act: -0.0001

Data Index: 213233 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6363. Min Act: -0.0001

Data Index: 26961 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6243. Min Act: -0.0001

Data Index: 120956 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.4916. Min Act: -0.0001

Data Index: 1124144 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.3228. Min Act: -0.0001

Data Index: 1065330 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.4447. Min Act: -0.0001

Data Index: 916616 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6019. Min Act: -0.0001

Data Index: 606221 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.2088. Min Act: -0.0001

Data Index: 1128416 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.4595. Min Act: -0.0001

Data Index: 773709 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.3006. Min Act: -0.0001

Data Index: 18140 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.3164. Min Act: -0.0001

Data Index: 258983 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.0929. Min Act: -0.0001

Data Index: 183873 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.0254. Min Act: -0.0001

Data Index: 382337 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 3.9879. Min Range: -3.9879

Max Act: 2.9870. Min Act: -0.0001

Data Index: 91980 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.1044. Min Act: -0.0001

Data Index: 560326 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.9879. Min Range: -3.9879

Max Act: 2.9633. Min Act: -0.0001

Data Index: 917799 (C4 (Web Text))

Max Activating Token Index: 682