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

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

Neuron 1133 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3076. Min Range: -6.3076

Max Act: 6.3076. Min Act: -0.0001

Data Index: 320357 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 6.3076. Min Range: -6.3076

Max Act: 4.2728. Min Act: -0.0001

Data Index: 1086041 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 6.3076. Min Range: -6.3076

Max Act: 4.4340. Min Act: -0.0000

Data Index: 22883 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.9671. Min Act: -0.0001

Data Index: 751862 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 6.3076. Min Range: -6.3076

Max Act: 4.2732. Min Act: -0.0000

Data Index: 1166824 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 6.3076. Min Range: -6.3076

Max Act: 4.3467. Min Act: -0.0000

Data Index: 946444 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.7764. Min Act: -0.0001

Data Index: 176440 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.9486. Min Act: -0.0001

Data Index: 536126 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.6510. Min Act: -0.0001

Data Index: 208386 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.6037. Min Act: -0.0000

Data Index: 623449 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.5235. Min Act: -0.0000

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.4634. Min Act: -0.0000

Data Index: 417013 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.5425. Min Act: -0.0000

Data Index: 620209 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.5345. Min Act: -0.0001

Data Index: 603158 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.2729. Min Act: -0.0000

Data Index: 534690 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.1384. Min Act: -0.0001

Data Index: 154462 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.1316. Min Act: -0.0000

Data Index: 800153 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 6.3076. Min Range: -6.3076

Max Act: 3.2675. Min Act: -0.0001

Data Index: 1126060 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 6.3076. Min Range: -6.3076

Max Act: 2.9476. Min Act: -0.0001

Data Index: 242521 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 6.3076. Min Range: -6.3076

Max Act: 2.9994. Min Act: -0.0001

Data Index: 673190 (C4 (Web Text))

Max Activating Token Index: 202