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

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

Neuron 2610 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: 3.3549. Min Range: -3.3549

Max Act: 3.3549. Min Act: -0.0000

Data Index: 1007384 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1806. Min Act: -0.0000

Data Index: 856413 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.5198. Min Act: -0.0000

Data Index: 210164 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.6966. Min Act: -0.0000

Data Index: 1124387 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.3370. Min Act: -0.0000

Data Index: 44997 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.9999. Min Act: -0.0000

Data Index: 1354332 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.7077. Min Act: -0.0000

Data Index: 479114 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.6355. Min Act: -0.0000

Data Index: 970135 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.2046. Min Act: -0.0000

Data Index: 433591 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.1998. Min Act: -0.0000

Data Index: 822744 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.0901. Min Act: -0.0000

Data Index: 936339 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.2869. Min Act: -0.0000

Data Index: 1555264 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.6500. Min Act: -0.0000

Data Index: 1020882 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.3933. Min Act: -0.0000

Data Index: 795729 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 3.3549. Min Range: -3.3549

Max Act: 1.6567. Min Act: -0.0000

Data Index: 1589384 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.2208. Min Act: -0.0000

Data Index: 672784 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 3.3549. Min Range: -3.3549

Max Act: 1.9646. Min Act: -0.0000

Data Index: 355560 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 3.3549. Min Range: -3.3549

Max Act: 2.0691. Min Act: -0.0000

Data Index: 667808 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 3.3549. Min Range: -3.3549

Max Act: 1.9767. Min Act: -0.0000

Data Index: 3590 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.3549. Min Range: -3.3549

Max Act: 1.9863. Min Act: -0.0000

Data Index: 1331210 (C4 (Web Text))

Max Activating Token Index: 520