Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7852. Min Act: -0.0001

Data Index: 551763 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.7169. Min Act: -0.0000

Data Index: 287272 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1054757 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1183831 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6538. Min Act: -0.0000

Data Index: 49274 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6824. Min Act: -0.0000

Data Index: 40322 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6290. Min Act: -0.0001

Data Index: 1066139 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1065849 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6336. Min Act: -0.0000

Data Index: 399839 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6104. Min Act: -0.0001

Data Index: 1408174 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6052. Min Act: -0.0000

Data Index: 62839 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6413. Min Act: -0.0000

Data Index: 934739 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6214. Min Act: -0.0001

Data Index: 1341429 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5986. Min Act: -0.0000

Data Index: 250585 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6131. Min Act: -0.0000

Data Index: 617068 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1063403 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5819. Min Act: -0.0001

Data Index: 771632 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5652. Min Act: -0.0000

Data Index: 226554 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.5826. Min Act: -0.0000

Data Index: 667808 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.7852. Min Range: -0.7852

Max Act: 0.6017. Min Act: -0.0001

Data Index: 780272 (C4 (Web Text))

Max Activating Token Index: 873