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

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

Neuron 1672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1204583 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8044. Min Act: 0.0000

Data Index: 350866 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7343. Min Act: 0.0000

Data Index: 1317513 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7186. Min Act: 0.0001

Data Index: 834155 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6653. Min Act: -0.0000

Data Index: 38517 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6588. Min Act: -0.0000

Data Index: 170915 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1253090 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1316012 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6316. Min Act: 0.0001

Data Index: 324214 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6585. Min Act: -0.0000

Data Index: 735368 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1249770 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5852. Min Act: -0.0000

Data Index: 361791 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6119. Min Act: -0.0000

Data Index: 761820 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5921. Min Act: -0.0000

Data Index: 137730 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5911. Min Act: -0.0000

Data Index: 986689 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5873. Min Act: -0.0000

Data Index: 440716 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5876. Min Act: -0.0000

Data Index: 994172 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5697. Min Act: -0.0000

Data Index: 702693 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5792. Min Act: 0.0001

Data Index: 327195 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5991. Min Act: 0.0000

Data Index: 747885 (C4 (Web Text))

Max Activating Token Index: 396