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

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

Neuron 4765 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.7861. Min Act: -0.0000

Data Index: 27773 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.3711. Min Act: 0.0001

Data Index: 601005 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.3084. Min Act: -0.0000

Data Index: 412227 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.1851. Min Act: -0.0000

Data Index: 226969 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.1250. Min Act: -0.0000

Data Index: 509836 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.1021. Min Act: -0.0000

Data Index: 681308 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.0646. Min Act: -0.0000

Data Index: 18721 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.0571. Min Act: -0.0000

Data Index: 282894 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.0740. Min Act: -0.0000

Data Index: 919665 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1069299 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.0472. Min Act: -0.0000

Data Index: 551768 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.9530. Min Act: -0.0000

Data Index: 276721 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.9589. Min Act: -0.0000

Data Index: 443677 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.9141. Min Act: -0.0000

Data Index: 915813 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.9195. Min Act: -0.0000

Data Index: 27939 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.8394. Min Act: -0.0000

Data Index: 87595 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.7861. Min Range: -1.7861

Max Act: 1.0112. Min Act: -0.0000

Data Index: 839564 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.9783. Min Act: -0.0000

Data Index: 664550 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.7861. Min Range: -1.7861

Max Act: 0.8554. Min Act: -0.0000

Data Index: 540300 (C4 (Web Text))

Max Activating Token Index: 239