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

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

Neuron 2988 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.3720. Min Act: -0.0000

Data Index: 373737 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1743. Min Act: -0.0000

Data Index: 351183 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1011067 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0377. Min Act: -0.0000

Data Index: 121725 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0274. Min Act: -0.0000

Data Index: 846624 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9792. Min Act: -0.0000

Data Index: 252578 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0377. Min Act: -0.0000

Data Index: 607507 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9699. Min Act: -0.0000

Data Index: 39721 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1086897 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9095. Min Act: -0.0000

Data Index: 828224 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9171. Min Act: -0.0000

Data Index: 472789 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1612349 (Python Code)

Max Activating Token Index: 215

Text #12

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1278487 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1226117 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9214. Min Act: -0.0000

Data Index: 616705 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8963. Min Act: -0.0000

Data Index: 45121 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8656. Min Act: -0.0000

Data Index: 546027 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1286417 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9064. Min Act: -0.0000

Data Index: 148903 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1333104 (C4 (Web Text))

Max Activating Token Index: 84