Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2786 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.6396. Min Act: -0.0000

Data Index: 483604 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.6342. Min Act: -0.0000

Data Index: 376847 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5925. Min Act: -0.0000

Data Index: 887996 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5836. Min Act: -0.0000

Data Index: 831667 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.6002. Min Act: -0.0000

Data Index: 232201 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5903. Min Act: -0.0000

Data Index: 354895 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5904. Min Act: -0.0000

Data Index: 851538 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5878. Min Act: -0.0000

Data Index: 609089 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5433. Min Act: -0.0000

Data Index: 379811 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5847. Min Act: -0.0000

Data Index: 355092 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5596. Min Act: -0.0000

Data Index: 577279 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5486. Min Act: -0.0001

Data Index: 682818 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5536. Min Act: -0.0000

Data Index: 545742 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1242764 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5454. Min Act: -0.0000

Data Index: 443395 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5411. Min Act: -0.0000

Data Index: 191343 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5384. Min Act: -0.0000

Data Index: 917467 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5192. Min Act: -0.0000

Data Index: 367682 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5483. Min Act: -0.0000

Data Index: 313993 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.6396. Min Range: -0.6396

Max Act: 0.5349. Min Act: -0.0000

Data Index: 303998 (C4 (Web Text))

Max Activating Token Index: 539