Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2872 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1203765 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5181. Min Act: -0.0000

Data Index: 100801 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5009. Min Act: -0.0000

Data Index: 596392 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1206132 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1338416 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1231026 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4927. Min Act: -0.0000

Data Index: 109894 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4596. Min Act: -0.0000

Data Index: 887036 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1335344 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4199. Min Act: -0.0000

Data Index: 545678 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4524. Min Act: -0.0000

Data Index: 99535 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4259. Min Act: -0.0000

Data Index: 626597 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.3929. Min Act: -0.0000

Data Index: 240432 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1203590 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.3878. Min Act: -0.0000

Data Index: 340845 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1042443 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.3473. Min Act: -0.0000

Data Index: 660904 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.3460. Min Act: -0.0000

Data Index: 637738 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.3438. Min Act: -0.0000

Data Index: 683848 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.5740. Min Range: -0.5740

Max Act: 0.3546. Min Act: -0.0000

Data Index: 705241 (C4 (Web Text))

Max Activating Token Index: 261