Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1482 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.1757. Min Act: -0.0001

Data Index: 1199608 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1110469 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1316554 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0203. Min Act: -0.0001

Data Index: 34798 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9816. Min Act: -0.0001

Data Index: 296136 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0504. Min Act: -0.0001

Data Index: 940962 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0102. Min Act: -0.0001

Data Index: 1293185 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9590. Min Act: -0.0001

Data Index: 976187 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8839. Min Act: -0.0001

Data Index: 41251 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9419. Min Act: -0.0000

Data Index: 980397 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8990. Min Act: -0.0001

Data Index: 582666 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1037046 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8429. Min Act: -0.0000

Data Index: 298093 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8983. Min Act: -0.0001

Data Index: 850832 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8716. Min Act: -0.0001

Data Index: 1519300 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9482. Min Act: -0.0001

Data Index: 960377 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8327. Min Act: -0.0000

Data Index: 887732 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1165049 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9395. Min Act: -0.0001

Data Index: 1097405 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8535. Min Act: -0.0001

Data Index: 308401 (C4 (Web Text))

Max Activating Token Index: 224