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

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

Neuron 2853 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8595. Min Act: -0.0001

Data Index: 985647 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1153534 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1293332 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1262229 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8169. Min Act: -0.0000

Data Index: 724356 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7530. Min Act: -0.0000

Data Index: 594094 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7483. Min Act: -0.0000

Data Index: 738417 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7435. Min Act: -0.0000

Data Index: 444813 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7418. Min Act: -0.0000

Data Index: 679392 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1118415 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7283. Min Act: -0.0000

Data Index: 702676 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7170. Min Act: -0.0000

Data Index: 818409 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7044. Min Act: -0.0000

Data Index: 733091 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6822. Min Act: -0.0001

Data Index: 404688 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7278. Min Act: -0.0000

Data Index: 539678 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7493. Min Act: -0.0000

Data Index: 457186 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6882. Min Act: -0.0000

Data Index: 929077 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6594. Min Act: -0.0000

Data Index: 459652 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6550. Min Act: -0.0000

Data Index: 61046 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6571. Min Act: -0.0001

Data Index: 28049 (C4 (Web Text))

Max Activating Token Index: 752