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

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

Neuron 5148 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: 1.9955. Min Range: -1.9955

Max Act: 1.9955. Min Act: -0.0000

Data Index: 22442 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7633. Min Act: -0.0000

Data Index: 322934 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7277. Min Act: -0.0000

Data Index: 1318646 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5507. Min Act: -0.0000

Data Index: 491738 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.4286. Min Act: -0.0000

Data Index: 409308 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7973. Min Act: -0.0000

Data Index: 1021692 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6808. Min Act: -0.0000

Data Index: 1091782 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6560. Min Act: -0.0000

Data Index: 222709 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6475. Min Act: -0.0000

Data Index: 530619 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6402. Min Act: -0.0000

Data Index: 616033 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6384. Min Act: -0.0000

Data Index: 918790 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5374. Min Act: -0.0000

Data Index: 346342 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5796. Min Act: -0.0000

Data Index: 742419 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.4792. Min Act: -0.0000

Data Index: 201096 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.4588. Min Act: -0.0000

Data Index: 39784 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.3388. Min Act: -0.0000

Data Index: 1081323 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5111. Min Act: -0.0000

Data Index: 177 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.4216. Min Act: -0.0000

Data Index: 547620 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.3908. Min Act: -0.0000

Data Index: 803338 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5334. Min Act: -0.0000

Data Index: 1130794 (C4 (Web Text))

Max Activating Token Index: 799