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

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

Neuron 2784 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0130. Min Act: -0.0003

Data Index: 680655 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1490533 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0112. Min Act: -0.0003

Data Index: 429729 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0003

Data Index: 697813 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0107. Min Act: -0.0003

Data Index: 602018 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0106. Min Act: -0.0003

Data Index: 465843 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1565603 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0103. Min Act: -0.0003

Data Index: 501017 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0103. Min Act: -0.0003

Data Index: 823682 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0100. Min Act: -0.0003

Data Index: 214721 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0098. Min Act: -0.0003

Data Index: 365736 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1384892 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0099. Min Act: -0.0003

Data Index: 361993 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0098. Min Act: -0.0003

Data Index: 507346 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1363299 (Python Code)

Max Activating Token Index: 579

Text #15

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0098. Min Act: -0.0003

Data Index: 12163 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0098. Min Act: -0.0003

Data Index: 361714 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0097. Min Act: -0.0003

Data Index: 200662 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1472533 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0097. Min Act: -0.0003

Data Index: 995655 (C4 (Web Text))

Max Activating Token Index: 681