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

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

Neuron 1784 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.9765. Min Act: -0.0000

Data Index: 969380 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1631653 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.8436. Min Act: -0.0000

Data Index: 434328 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.8723. Min Act: -0.0000

Data Index: 44988 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.8160. Min Act: -0.0000

Data Index: 752492 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1352987 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7272. Min Act: -0.0000

Data Index: 860084 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7627. Min Act: -0.0000

Data Index: 653380 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7874. Min Act: -0.0000

Data Index: 548625 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1181121 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7709. Min Act: -0.0000

Data Index: 306001 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1605321 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7387. Min Act: -0.0000

Data Index: 522336 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1632447 (Python Code)

Max Activating Token Index: 948

Text #14

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1567229 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7071. Min Act: -0.0000

Data Index: 782392 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7239. Min Act: -0.0000

Data Index: 396502 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1533647 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7374. Min Act: -0.0000

Data Index: 66370 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1398667 (Python Code)

Max Activating Token Index: 471