Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2709 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.5858. Min Act: -0.0000

Data Index: 567247 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2198. Min Act: -0.0000

Data Index: 1056678 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.1898. Min Act: -0.0000

Data Index: 350856 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.0785. Min Act: -0.0000

Data Index: 970526 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.8051. Min Act: -0.0000

Data Index: 769107 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.5220. Min Act: -0.0000

Data Index: 249542 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.6131. Min Act: -0.0000

Data Index: 1064273 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.4663. Min Act: -0.0000

Data Index: 257962 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.1120. Min Act: -0.0000

Data Index: 198551 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.0837. Min Act: -0.0000

Data Index: 491151 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1298361 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.5858. Min Range: -3.5858

Max Act: 2.0857. Min Act: -0.0000

Data Index: 1162385 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.9416. Min Act: -0.0000

Data Index: 666585 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.8404. Min Act: -0.0000

Data Index: 833780 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.9734. Min Act: -0.0000

Data Index: 460994 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.7541. Min Act: -0.0000

Data Index: 533617 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.7487. Min Act: -0.0000

Data Index: 913753 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.5512. Min Act: -0.0000

Data Index: 1433427 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.6465. Min Act: -0.0000

Data Index: 170173 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 3.5858. Min Range: -3.5858

Max Act: 1.5410. Min Act: -0.0000

Data Index: 414883 (C4 (Web Text))

Max Activating Token Index: 958