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

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

Neuron 1565 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: 2.5573. Min Range: -2.5573

Max Act: 2.5573. Min Act: -0.0000

Data Index: 282658 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.5458. Min Act: -0.0000

Data Index: 132111 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.3965. Min Act: -0.0000

Data Index: 733903 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.2935. Min Act: -0.0000

Data Index: 376422 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.2625. Min Act: -0.0000

Data Index: 918527 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.2253. Min Act: -0.0000

Data Index: 167269 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.2316. Min Act: -0.0000

Data Index: 599494 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.2552. Min Act: -0.0000

Data Index: 772343 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.0187. Min Act: -0.0000

Data Index: 951277 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.1043. Min Act: -0.0000

Data Index: 1020156 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.9798. Min Act: -0.0000

Data Index: 515062 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.9633. Min Act: -0.0000

Data Index: 884557 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 2.5573. Min Range: -2.5573

Max Act: 2.0515. Min Act: -0.0000

Data Index: 874538 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.8789. Min Act: -0.0000

Data Index: 156198 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.8914. Min Act: -0.0000

Data Index: 773491 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.6708. Min Act: -0.0000

Data Index: 797859 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.8157. Min Act: -0.0000

Data Index: 318325 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.8112. Min Act: -0.0000

Data Index: 834222 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.8980. Min Act: -0.0000

Data Index: 98279 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 2.5573. Min Range: -2.5573

Max Act: 1.6745. Min Act: -0.0000

Data Index: 781954 (C4 (Web Text))

Max Activating Token Index: 821