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

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

Neuron 5805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5171. Min Range: -5.5171

Max Act: 5.3188. Min Act: -0.0000

Data Index: 518045 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 5.5171. Min Range: -5.5171

Max Act: 5.5171. Min Act: -0.0000

Data Index: 1350339 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 5.5171. Min Range: -5.5171

Max Act: 5.2919. Min Act: -0.0000

Data Index: 1347360 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 5.5171. Min Range: -5.5171

Max Act: 5.1527. Min Act: -0.0000

Data Index: 70189 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.8996. Min Act: -0.0000

Data Index: 56741 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.9973. Min Act: -0.0000

Data Index: 902611 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.9722. Min Act: -0.0000

Data Index: 530152 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.8963. Min Act: -0.0000

Data Index: 668285 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.6629. Min Act: -0.0000

Data Index: 487911 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.6803. Min Act: -0.0000

Data Index: 547183 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.5256. Min Act: -0.0000

Data Index: 246292 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.5167. Min Act: -0.0000

Data Index: 813767 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.3999. Min Act: -0.0000

Data Index: 1313173 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.3585. Min Act: -0.0000

Data Index: 550160 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.1084. Min Act: -0.0000

Data Index: 1351185 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 5.5171. Min Range: -5.5171

Max Act: 3.9610. Min Act: -0.0000

Data Index: 705252 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 5.5171. Min Range: -5.5171

Max Act: 3.9138. Min Act: -0.0000

Data Index: 387419 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 5.5171. Min Range: -5.5171

Max Act: 4.0757. Min Act: -0.0000

Data Index: 224583 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 5.5171. Min Range: -5.5171

Max Act: 3.8460. Min Act: -0.0000

Data Index: 1137814 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 5.5171. Min Range: -5.5171

Max Act: 3.8006. Min Act: -0.0000

Data Index: 227326 (C4 (Web Text))

Max Activating Token Index: 61