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

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

Neuron 3673 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4381. Min Act: -0.0001

Data Index: 1256203 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4084. Min Act: -0.0001

Data Index: 1073374 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3822. Min Act: -0.0001

Data Index: 141510 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3859. Min Act: -0.0001

Data Index: 195259 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3754. Min Act: -0.0001

Data Index: 581112 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4011. Min Act: -0.0001

Data Index: 1099696 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3777. Min Act: -0.0001

Data Index: 938853 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3797. Min Act: -0.0001

Data Index: 170640 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1283379 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3643. Min Act: -0.0001

Data Index: 1184546 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3739. Min Act: -0.0001

Data Index: 1011565 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3812. Min Act: -0.0001

Data Index: 316109 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3613. Min Act: -0.0001

Data Index: 879752 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3551. Min Act: -0.0001

Data Index: 208527 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3755. Min Act: -0.0001

Data Index: 292854 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3261. Min Act: -0.0001

Data Index: 328999 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3244. Min Act: -0.0001

Data Index: 891253 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3204. Min Act: -0.0001

Data Index: 723572 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3418. Min Act: -0.0001

Data Index: 1003345 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1294940 (C4 (Web Text))

Max Activating Token Index: 190