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

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

Neuron 3096 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.5448. Min Act: -0.0000

Data Index: 940926 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.5910. Min Act: -0.0000

Data Index: 313066 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1013054 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4797. Min Act: -0.0000

Data Index: 796472 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4995. Min Act: -0.0000

Data Index: 385095 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4623. Min Act: -0.0000

Data Index: 214645 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4066. Min Act: -0.0000

Data Index: 6701 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1287162 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3934. Min Act: -0.0000

Data Index: 679101 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1206088 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3890. Min Act: -0.0000

Data Index: 39734 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3244. Min Act: -0.0000

Data Index: 976681 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1174936 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3855. Min Act: -0.0000

Data Index: 876145 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3433. Min Act: -0.0000

Data Index: 350586 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1061172 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1255921 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1348865 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1005190 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.5910. Min Range: -0.5910

Max Act: 0.3236. Min Act: -0.0000

Data Index: 51411 (C4 (Web Text))

Max Activating Token Index: 292