Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5410 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8361. Min Act: -0.0000

Data Index: 370777 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1092761 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7589. Min Act: -0.0000

Data Index: 850189 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 443285 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7381. Min Act: -0.0000

Data Index: 129220 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7208. Min Act: -0.0000

Data Index: 705262 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6678. Min Act: -0.0000

Data Index: 554390 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7415. Min Act: -0.0000

Data Index: 821627 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7062. Min Act: -0.0000

Data Index: 200356 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6542. Min Act: -0.0000

Data Index: 178926 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5893. Min Act: -0.0000

Data Index: 146327 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1429195 (Python Code)

Max Activating Token Index: 840

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6176. Min Act: -0.0000

Data Index: 837904 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1343150 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1398119 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5976. Min Act: -0.0000

Data Index: 614095 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1488242 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5981. Min Act: -0.0000

Data Index: 949822 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5868. Min Act: 0.0000

Data Index: 514045 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5836. Min Act: -0.0000

Data Index: 571176 (C4 (Web Text))

Max Activating Token Index: 310