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

Dataset: The Pile

Neuron 3478 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1931114 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1868017 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1755068 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1863772 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5412. Min Act: -0.0000

Data Index: 549948 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5151. Min Act: -0.0000

Data Index: 757955 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1432928 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1005371 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5007. Min Act: -0.0000

Data Index: 224633 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1475838 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1530555 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1162406 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1958391 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1562650 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4864. Min Act: -0.0000

Data Index: 216358 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1574208 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4893. Min Act: -0.0000

Data Index: 522802 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5240. Min Act: -0.0000

Data Index: 805427 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1940491 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.4722. Min Act: -0.0000

Data Index: 635950 (The Pile)

Max Activating Token Index: 262