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

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

Neuron 1430 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.2087. Min Act: -0.0001

Data Index: 34372 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.1153. Min Act: -0.0001

Data Index: 836299 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0754. Min Act: -0.0001

Data Index: 1344679 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.1037. Min Act: -0.0001

Data Index: 58421 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.1749. Min Act: -0.0001

Data Index: 947426 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.1022. Min Act: -0.0001

Data Index: 151201 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0969. Min Act: -0.0001

Data Index: 494187 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.9955. Min Act: -0.0001

Data Index: 1065962 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.9851. Min Act: -0.0001

Data Index: 671338 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0352. Min Act: -0.0001

Data Index: 185882 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0170. Min Act: -0.0001

Data Index: 959108 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0506. Min Act: -0.0001

Data Index: 478774 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0296. Min Act: -0.0001

Data Index: 291442 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.9775. Min Act: -0.0001

Data Index: 278758 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0912. Min Act: -0.0001

Data Index: 796364 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1173726 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0147. Min Act: -0.0001

Data Index: 316249 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.8832. Min Act: -0.0001

Data Index: 1346472 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.8813. Min Act: -0.0001

Data Index: 143512 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.8893. Min Act: -0.0001

Data Index: 271694 (C4 (Web Text))

Max Activating Token Index: 698