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

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

Neuron 4140 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.6282. Min Act: 0.0000

Data Index: 662676 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.5881. Min Act: -0.0000

Data Index: 609781 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.6190. Min Act: -0.0000

Data Index: 330 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.6083. Min Act: -0.0000

Data Index: 352362 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.5551. Min Act: -0.0000

Data Index: 109004 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.5029. Min Act: -0.0000

Data Index: 627288 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.5010. Min Act: -0.0000

Data Index: 612485 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4757. Min Act: -0.0000

Data Index: 951971 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1368747 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4603. Min Act: -0.0000

Data Index: 280115 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1064721 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4008. Min Act: 0.0000

Data Index: 988937 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1150666 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4004. Min Act: 0.0000

Data Index: 486868 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4032. Min Act: 0.0000

Data Index: 1274067 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1465324 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3864. Min Act: -0.0000

Data Index: 483459 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1160145 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1190652 (C4 (Web Text))

Max Activating Token Index: 821