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

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

Neuron 2452 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: 0.8800. Min Range: -0.8800

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1322291 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1192081 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.7509. Min Act: -0.0000

Data Index: 806502 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.7520. Min Act: -0.0000

Data Index: 545570 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1331939 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.7035. Min Act: -0.0000

Data Index: 363536 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.7168. Min Act: -0.0000

Data Index: 695801 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1265555 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6504. Min Act: -0.0000

Data Index: 474262 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6596. Min Act: -0.0001

Data Index: 1171117 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6598. Min Act: -0.0000

Data Index: 226496 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1243087 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6266. Min Act: -0.0000

Data Index: 414042 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6263. Min Act: -0.0000

Data Index: 917617 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6049. Min Act: -0.0000

Data Index: 195919 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.5945. Min Act: -0.0000

Data Index: 39891 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.6043. Min Act: -0.0000

Data Index: 940442 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.5818. Min Act: -0.0000

Data Index: 505881 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.5991. Min Act: -0.0000

Data Index: 970452 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.8800. Min Range: -0.8800

Max Act: 0.5785. Min Act: -0.0000

Data Index: 649832 (C4 (Web Text))

Max Activating Token Index: 924