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

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

Neuron 2914 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2069. Min Range: -1.2069

Max Act: 1.2069. Min Act: -0.0000

Data Index: 141436 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.2069. Min Range: -1.2069

Max Act: 1.1836. Min Act: -0.0000

Data Index: 987089 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.2069. Min Range: -1.2069

Max Act: 1.1945. Min Act: -0.0000

Data Index: 965316 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.2069. Min Range: -1.2069

Max Act: 1.0026. Min Act: -0.0000

Data Index: 630757 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.9458. Min Act: -0.0000

Data Index: 385832 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.9283. Min Act: -0.0000

Data Index: 79526 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1058892 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1318208 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8580. Min Act: -0.0000

Data Index: 660715 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.9146. Min Act: -0.0000

Data Index: 276145 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7947. Min Act: -0.0000

Data Index: 131831 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8481. Min Act: -0.0000

Data Index: 545429 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8316. Min Act: -0.0000

Data Index: 200944 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1185272 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8489. Min Act: -0.0000

Data Index: 136424 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8500. Min Act: -0.0000

Data Index: 253171 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8387. Min Act: -0.0000

Data Index: 964070 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1136857 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7701. Min Act: -0.0000

Data Index: 788244 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7914. Min Act: -0.0000

Data Index: 222568 (C4 (Web Text))

Max Activating Token Index: 22