Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1955 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1333. Min Act: -0.0002

Data Index: 760029 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0002

Data Index: 899535 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1340. Min Act: -0.0002

Data Index: 847561 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1240827 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1283. Min Act: -0.0002

Data Index: 15091 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1340. Min Act: -0.0002

Data Index: 127770 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1241. Min Act: -0.0002

Data Index: 295538 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1319. Min Act: -0.0002

Data Index: 640076 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1264. Min Act: -0.0002

Data Index: 401504 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1167. Min Act: -0.0002

Data Index: 489427 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0991. Min Act: -0.0002

Data Index: 670528 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1221484 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1013. Min Act: -0.0002

Data Index: 83509 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0999. Min Act: -0.0002

Data Index: 453568 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1194. Min Act: -0.0002

Data Index: 618685 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0959. Min Act: -0.0002

Data Index: 620475 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1066. Min Act: -0.0002

Data Index: 376643 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1131257 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1312392 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1080. Min Act: -0.0002

Data Index: 673716 (C4 (Web Text))

Max Activating Token Index: 300