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

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

Neuron 903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0475. Min Range: -1.0475

Max Act: 1.0475. Min Act: -0.0001

Data Index: 1260858 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9846. Min Act: -0.0001

Data Index: 41180 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 1.0475. Min Range: -1.0475

Max Act: 1.0337. Min Act: -0.0002

Data Index: 148537 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8785. Min Act: -0.0001

Data Index: 663955 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9654. Min Act: -0.0002

Data Index: 879110 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8326. Min Act: -0.0001

Data Index: 214061 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.0475. Min Range: -1.0475

Max Act: 1.0071. Min Act: -0.0001

Data Index: 152478 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9051. Min Act: -0.0001

Data Index: 353228 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9261. Min Act: -0.0002

Data Index: 566876 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9495. Min Act: -0.0001

Data Index: 286564 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8360. Min Act: -0.0002

Data Index: 890126 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 1.0475. Min Range: -1.0475

Max Act: 1.0050. Min Act: -0.0001

Data Index: 442277 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8608. Min Act: -0.0002

Data Index: 216505 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1184251 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8233. Min Act: -0.0002

Data Index: 702003 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8901. Min Act: -0.0001

Data Index: 365896 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8428. Min Act: -0.0001

Data Index: 973784 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.7333. Min Act: -0.0002

Data Index: 1326523 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8380. Min Act: -0.0001

Data Index: 573667 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.7905. Min Act: -0.0001

Data Index: 1296439 (C4 (Web Text))

Max Activating Token Index: 906