Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2586 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3135. Min Range: -1.3135

Max Act: 1.3135. Min Act: -0.0000

Data Index: 197792 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.3135. Min Range: -1.3135

Max Act: 1.3116. Min Act: -0.0000

Data Index: 724341 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.3135. Min Range: -1.3135

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1059853 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.3135. Min Range: -1.3135

Max Act: 1.1806. Min Act: -0.0000

Data Index: 882523 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.3135. Min Range: -1.3135

Max Act: 1.0067. Min Act: -0.0000

Data Index: 732011 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 1.3135. Min Range: -1.3135

Max Act: 1.0076. Min Act: -0.0000

Data Index: 809586 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9857. Min Act: -0.0000

Data Index: 799844 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9735. Min Act: -0.0000

Data Index: 744535 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9685. Min Act: -0.0000

Data Index: 357972 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.3135. Min Range: -1.3135

Max Act: 1.0244. Min Act: -0.0000

Data Index: 873658 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9024. Min Act: -0.0000

Data Index: 386529 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9523. Min Act: -0.0000

Data Index: 510659 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9105. Min Act: -0.0000

Data Index: 726343 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.8847. Min Act: -0.0000

Data Index: 267717 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.8783. Min Act: -0.0000

Data Index: 913501 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.7992. Min Act: -0.0000

Data Index: 683827 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9036. Min Act: -0.0000

Data Index: 10404 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.7923. Min Act: -0.0000

Data Index: 317360 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.9682. Min Act: -0.0000

Data Index: 76557 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.3135. Min Range: -1.3135

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1137536 (C4 (Web Text))

Max Activating Token Index: 853