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

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

Neuron 1084 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: 1.8460. Min Range: -1.8460

Max Act: 1.8165. Min Act: -0.0000

Data Index: 457899 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.6976. Min Act: -0.0000

Data Index: 846447 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.8460. Min Act: -0.0000

Data Index: 416299 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1172380 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2908. Min Act: -0.0000

Data Index: 876179 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1000067 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.4131. Min Act: -0.0000

Data Index: 284010 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3196. Min Act: -0.0000

Data Index: 445789 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2662. Min Act: -0.0000

Data Index: 785523 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1263088 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1398. Min Act: -0.0000

Data Index: 228077 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1527886 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0094. Min Act: -0.0000

Data Index: 320672 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0588. Min Act: -0.0000

Data Index: 635770 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1025764 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0206. Min Act: -0.0000

Data Index: 286310 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.8460. Min Range: -1.8460

Max Act: 0.9588. Min Act: -0.0000

Data Index: 506143 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0655. Min Act: -0.0000

Data Index: 807107 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0440. Min Act: -0.0000

Data Index: 473593 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.8460. Min Range: -1.8460

Max Act: 0.9254. Min Act: -0.0000

Data Index: 410310 (C4 (Web Text))

Max Activating Token Index: 909