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

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

Neuron 2731 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.9764. Min Act: -0.0000

Data Index: 15114 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.8479. Min Act: -0.0000

Data Index: 475796 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.8524. Min Act: -0.0000

Data Index: 293504 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.6987. Min Act: -0.0000

Data Index: 184527 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1307013 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.7861. Min Act: 0.0000

Data Index: 181004 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1026250 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.7465. Min Act: -0.0000

Data Index: 878071 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.7095. Min Act: -0.0000

Data Index: 1212724 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.8184. Min Act: -0.0000

Data Index: 713995 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.6141. Min Act: -0.0000

Data Index: 708086 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.5773. Min Act: -0.0000

Data Index: 792607 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.5530. Min Act: -0.0000

Data Index: 357168 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.5797. Min Act: 0.0000

Data Index: 73034 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.3233. Min Act: -0.0000

Data Index: 1197328 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.5767. Min Act: -0.0000

Data Index: 193058 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.5797. Min Act: -0.0000

Data Index: 85548 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.5764. Min Act: -0.0000

Data Index: 949472 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.4365. Min Act: -0.0000

Data Index: 1242173 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 2.9764. Min Range: -2.9764

Max Act: 2.2953. Min Act: -0.0000

Data Index: 331459 (C4 (Web Text))

Max Activating Token Index: 223