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

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

Neuron 1540 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0465. Min Range: -1.0465

Max Act: 1.0465. Min Act: -0.0000

Data Index: 768189 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8073. Min Act: -0.0001

Data Index: 1157801 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1056469 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8504. Min Act: -0.0000

Data Index: 193337 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8668. Min Act: -0.0000

Data Index: 152705 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8295. Min Act: -0.0001

Data Index: 818044 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7961. Min Act: -0.0001

Data Index: 482776 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7991. Min Act: -0.0000

Data Index: 79279 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7506. Min Act: -0.0000

Data Index: 887647 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1352093 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7421. Min Act: -0.0000

Data Index: 570301 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1306282 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1290722 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7584. Min Act: -0.0001

Data Index: 250785 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7234. Min Act: -0.0000

Data Index: 360774 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7209. Min Act: -0.0000

Data Index: 991957 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1327554 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7286. Min Act: -0.0001

Data Index: 389096 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7082. Min Act: -0.0001

Data Index: 426323 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6834. Min Act: -0.0000

Data Index: 735274 (C4 (Web Text))

Max Activating Token Index: 562