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

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

Neuron 3485 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9606. Min Act: -0.0000

Data Index: 190941 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7340. Min Act: -0.0000

Data Index: 936723 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7280. Min Act: -0.0000

Data Index: 190789 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1308253 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1156935 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6549. Min Act: -0.0000

Data Index: 555241 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1286186 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1194990 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6142. Min Act: -0.0000

Data Index: 988583 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6250. Min Act: -0.0000

Data Index: 94075 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5974. Min Act: -0.0000

Data Index: 573146 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5995. Min Act: -0.0000

Data Index: 768050 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6151. Min Act: -0.0000

Data Index: 933343 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6292. Min Act: -0.0000

Data Index: 847115 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5783. Min Act: -0.0000

Data Index: 563807 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6101. Min Act: -0.0000

Data Index: 452057 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5871. Min Act: -0.0000

Data Index: 612482 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5663. Min Act: -0.0000

Data Index: 784956 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5674. Min Act: -0.0000

Data Index: 598513 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1108330 (C4 (Web Text))

Max Activating Token Index: 61