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

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

Neuron 2251 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.7062. Min Act: -0.0000

Data Index: 938159 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.7681. Min Act: -0.0000

Data Index: 3804 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.8433. Min Act: -0.0001

Data Index: 1114182 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.1243. Min Act: -0.0000

Data Index: 91384 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.3151. Min Act: -0.0001

Data Index: 312074 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.3600. Min Act: -0.0001

Data Index: 404106 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.1779. Min Act: -0.0001

Data Index: 805817 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.7101. Min Act: -0.0000

Data Index: 828169 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.4336. Min Act: -0.0001

Data Index: 1176013 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.0556. Min Act: -0.0001

Data Index: 1019954 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 2.8433. Min Range: -2.8433

Max Act: 2.1119. Min Act: -0.0000

Data Index: 640971 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.9668. Min Act: -0.0001

Data Index: 1027453 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.8063. Min Act: -0.0001

Data Index: 1221367 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.8385. Min Act: -0.0000

Data Index: 613573 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.9402. Min Act: -0.0000

Data Index: 832848 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.9453. Min Act: -0.0001

Data Index: 471393 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.8853. Min Act: -0.0000

Data Index: 191838 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.5034. Min Act: -0.0000

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.6742. Min Act: -0.0001

Data Index: 1041514 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 2.8433. Min Range: -2.8433

Max Act: 1.4688. Min Act: -0.0001

Data Index: 17254 (C4 (Web Text))

Max Activating Token Index: 671