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

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

Neuron 5066 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1341. Min Range: -1.1341

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1007530 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.1341. Min Range: -1.1341

Max Act: 1.0951. Min Act: -0.0000

Data Index: 411707 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.1341. Min Range: -1.1341

Max Act: 1.0360. Min Act: -0.0000

Data Index: 374811 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 1.1341. Min Range: -1.1341

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1086109 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1213967 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9921. Min Act: -0.0000

Data Index: 749132 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9797. Min Act: -0.0000

Data Index: 946215 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9814. Min Act: -0.0000

Data Index: 637319 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1255196 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9658. Min Act: -0.0000

Data Index: 124200 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9626. Min Act: -0.0000

Data Index: 102765 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9606. Min Act: -0.0000

Data Index: 393844 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9570. Min Act: -0.0000

Data Index: 877071 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9407. Min Act: 0.0000

Data Index: 343917 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9368. Min Act: -0.0000

Data Index: 270862 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9040. Min Act: -0.0000

Data Index: 213997 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9003. Min Act: -0.0000

Data Index: 582067 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1221905 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1132198 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.8792. Min Act: -0.0000

Data Index: 413642 (C4 (Web Text))

Max Activating Token Index: 30