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

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

Neuron 24 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.2884. Min Act: -0.0000

Data Index: 425974 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1106804 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.2489. Min Act: -0.0000

Data Index: 460576 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1068405 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.1340. Min Act: -0.0000

Data Index: 241105 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1009705 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.1724. Min Act: -0.0000

Data Index: 324588 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9310. Min Act: -0.0000

Data Index: 784469 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1259125 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.0131. Min Act: -0.0000

Data Index: 749420 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.0066. Min Act: -0.0000

Data Index: 748252 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.0258. Min Act: -0.0000

Data Index: 969821 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1286739 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1264528 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1345582 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9052. Min Act: -0.0000

Data Index: 985426 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9358. Min Act: -0.0000

Data Index: 185592 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9311. Min Act: -0.0000

Data Index: 41313 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.2884. Min Range: -1.2884

Max Act: 1.0188. Min Act: -0.0000

Data Index: 475971 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 1.2884. Min Range: -1.2884

Max Act: 0.9325. Min Act: -0.0000

Data Index: 333683 (C4 (Web Text))

Max Activating Token Index: 361