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

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

Neuron 1886 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: 2.2435. Min Range: -2.2435

Max Act: 2.2435. Min Act: -0.0000

Data Index: 873877 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.9106. Min Act: -0.0000

Data Index: 1109804 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8847. Min Act: -0.0000

Data Index: 402419 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8699. Min Act: -0.0000

Data Index: 625460 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8580. Min Act: -0.0000

Data Index: 917265 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.9360. Min Act: -0.0000

Data Index: 163751 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.9138. Min Act: -0.0000

Data Index: 596415 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8209. Min Act: -0.0000

Data Index: 511317 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.9121. Min Act: -0.0000

Data Index: 597608 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8942. Min Act: -0.0000

Data Index: 803173 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8823. Min Act: -0.0000

Data Index: 385342 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8650. Min Act: -0.0000

Data Index: 517003 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8396. Min Act: -0.0000

Data Index: 356571 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.6875. Min Act: -0.0000

Data Index: 791731 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1172578 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.6375. Min Act: -0.0000

Data Index: 997446 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.8310. Min Act: -0.0000

Data Index: 815257 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.7337. Min Act: -0.0000

Data Index: 1183859 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.7155. Min Act: -0.0000

Data Index: 1226672 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 2.2435. Min Range: -2.2435

Max Act: 1.6933. Min Act: -0.0000

Data Index: 877389 (C4 (Web Text))

Max Activating Token Index: 450