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

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

Neuron 4838 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: 4.8893. Min Range: -4.8893

Max Act: 4.8893. Min Act: -0.0000

Data Index: 275483 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 4.8893. Min Range: -4.8893

Max Act: 4.3152. Min Act: -0.0000

Data Index: 571786 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.9650. Min Act: -0.0000

Data Index: 1359229 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 4.8893. Min Range: -4.8893

Max Act: 4.2355. Min Act: -0.0000

Data Index: 804909 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 4.8893. Min Range: -4.8893

Max Act: 4.3960. Min Act: -0.0000

Data Index: 851272 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.2743. Min Act: -0.0000

Data Index: 1174763 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.4290. Min Act: -0.0000

Data Index: 438854 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.4034. Min Act: -0.0000

Data Index: 830802 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.2178. Min Act: -0.0000

Data Index: 1289712 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.3042. Min Act: -0.0000

Data Index: 597548 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.2527. Min Act: -0.0000

Data Index: 740567 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.2328. Min Act: -0.0000

Data Index: 109552 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.1556. Min Act: -0.0000

Data Index: 1315884 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.0278. Min Act: -0.0000

Data Index: 498709 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.1145. Min Act: -0.0000

Data Index: 734786 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 4.8893. Min Range: -4.8893

Max Act: 2.9369. Min Act: -0.0000

Data Index: 627657 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.0106. Min Act: -0.0000

Data Index: 1291734 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.0123. Min Act: -0.0000

Data Index: 47662 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 4.8893. Min Range: -4.8893

Max Act: 3.1439. Min Act: -0.0000

Data Index: 838608 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 4.8893. Min Range: -4.8893

Max Act: 2.9900. Min Act: -0.0000

Data Index: 628758 (C4 (Web Text))

Max Activating Token Index: 849