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

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

Neuron 3366 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7840. Min Act: -0.0000

Data Index: 988527 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6374. Min Act: -0.0000

Data Index: 94177 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1001511 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6086. Min Act: -0.0000

Data Index: 998991 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1221473 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1021858 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5830. Min Act: -0.0000

Data Index: 930466 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5971. Min Act: -0.0000

Data Index: 800476 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1243302 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5564. Min Act: -0.0000

Data Index: 649306 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5483. Min Act: -0.0000

Data Index: 214140 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5349. Min Act: -0.0000

Data Index: 529124 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5398. Min Act: -0.0000

Data Index: 823200 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1242958 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5404. Min Act: -0.0000

Data Index: 364382 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1175604 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5472. Min Act: -0.0000

Data Index: 661399 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.4774. Min Act: -0.0000

Data Index: 798211 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1394392 (Python Code)

Max Activating Token Index: 176

Text #19

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5443. Min Act: -0.0000

Data Index: 303176 (C4 (Web Text))

Max Activating Token Index: 770