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

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

Neuron 1462 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: 0.8823. Min Range: -0.8823

Max Act: 0.8823. Min Act: -0.0001

Data Index: 1425566 (Python Code)

Max Activating Token Index: 523

Text #1

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7737. Min Act: -0.0000

Data Index: 570657 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6899. Min Act: -0.0001

Data Index: 1482121 (Python Code)

Max Activating Token Index: 800

Text #3

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1423452 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6171. Min Act: -0.0001

Data Index: 1383348 (Python Code)

Max Activating Token Index: 802

Text #5

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5378. Min Act: -0.0001

Data Index: 1570182 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1128786 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1427606 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1295590 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5717. Min Act: -0.0001

Data Index: 1346460 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4915. Min Act: -0.0000

Data Index: 397837 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5003. Min Act: -0.0001

Data Index: 1361483 (Python Code)

Max Activating Token Index: 725

Text #12

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4694. Min Act: -0.0001

Data Index: 1510504 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5232. Min Act: -0.0001

Data Index: 457174 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5071. Min Act: -0.0001

Data Index: 993143 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1488419 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4795. Min Act: -0.0001

Data Index: 1464717 (Python Code)

Max Activating Token Index: 700

Text #17

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1654058 (Python Code)

Max Activating Token Index: 669

Text #18

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1499228 (Python Code)

Max Activating Token Index: 716

Text #19

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4726. Min Act: -0.0001

Data Index: 1553652 (Python Code)

Max Activating Token Index: 997