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

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

Neuron 731 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5830. Min Act: -0.0000

Data Index: 251996 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1128793 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4952. Min Act: -0.0000

Data Index: 944052 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1185654 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3621. Min Act: -0.0000

Data Index: 931195 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1148416 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1175240 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3807. Min Act: -0.0000

Data Index: 877772 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1248888 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3656. Min Act: -0.0000

Data Index: 274380 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3815. Min Act: -0.0000

Data Index: 817454 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3994. Min Act: -0.0000

Data Index: 803824 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3637. Min Act: -0.0000

Data Index: 326382 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3735. Min Act: -0.0000

Data Index: 851607 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3662. Min Act: -0.0000

Data Index: 252238 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1351198 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3599. Min Act: -0.0000

Data Index: 819767 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3561. Min Act: -0.0000

Data Index: 454418 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3472. Min Act: -0.0000

Data Index: 573653 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3555. Min Act: -0.0000

Data Index: 970899 (C4 (Web Text))

Max Activating Token Index: 237