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

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

Neuron 4281 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0791. Min Range: -3.0791

Max Act: 3.0791. Min Act: -0.0000

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.7875. Min Act: -0.0000

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.9046. Min Act: -0.0000

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.7090. Min Act: -0.0000

Data Index: 971099 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.5313. Min Act: -0.0000

Data Index: 809993 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.2078. Min Act: -0.0000

Data Index: 641283 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1023807 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.1659. Min Act: -0.0000

Data Index: 551679 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.9884. Min Act: -0.0000

Data Index: 953776 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.0776. Min Act: -0.0000

Data Index: 237584 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.0832. Min Act: -0.0000

Data Index: 746653 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 3.0791. Min Range: -3.0791

Max Act: 2.0003. Min Act: -0.0000

Data Index: 517601 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1110352 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.9877. Min Act: -0.0000

Data Index: 232545 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.8638. Min Act: -0.0000

Data Index: 194718 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.9632. Min Act: -0.0000

Data Index: 238193 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.9576. Min Act: -0.0000

Data Index: 343327 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.9613. Min Act: -0.0000

Data Index: 1316400 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.9448. Min Act: -0.0000

Data Index: 284985 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 3.0791. Min Range: -3.0791

Max Act: 1.9202. Min Act: -0.0000

Data Index: 754746 (C4 (Web Text))

Max Activating Token Index: 822