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

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

Neuron 1868 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: 0.8495. Min Range: -0.8495

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1504256 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1516682 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1505326 (Python Code)

Max Activating Token Index: 192

Text #3

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1263418 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1495063 (Python Code)

Max Activating Token Index: 433

Text #5

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1089996 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6416. Min Act: -0.0000

Data Index: 207919 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1532308 (Python Code)

Max Activating Token Index: 861

Text #8

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6307. Min Act: -0.0000

Data Index: 652541 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1570015 (Python Code)

Max Activating Token Index: 872

Text #10

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1633923 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6019. Min Act: -0.0000

Data Index: 289855 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1515740 (Python Code)

Max Activating Token Index: 117

Text #13

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1473749 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5888. Min Act: -0.0000

Data Index: 39803 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1420947 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6003. Min Act: -0.0000

Data Index: 926269 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5755. Min Act: -0.0000

Data Index: 686595 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5740. Min Act: -0.0000

Data Index: 812568 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5693. Min Act: -0.0000

Data Index: 755298 (C4 (Web Text))

Max Activating Token Index: 935