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

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

Neuron 3288 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.3076. Min Act: -0.0000

Data Index: 704951 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.3142. Min Act: -0.0000

Data Index: 505573 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2934. Min Act: -0.0000

Data Index: 571513 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2841. Min Act: -0.0000

Data Index: 626142 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2685. Min Act: 0.0000

Data Index: 356910 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1379124 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2567. Min Act: -0.0000

Data Index: 223616 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2408. Min Act: 0.0000

Data Index: 756704 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2412. Min Act: -0.0000

Data Index: 715137 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2379. Min Act: -0.0000

Data Index: 405201 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2276. Min Act: 0.0000

Data Index: 688160 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2443. Min Act: -0.0000

Data Index: 106470 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1501543 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2342. Min Act: 0.0000

Data Index: 1158096 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1209077 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2252. Min Act: -0.0000

Data Index: 56112 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2251. Min Act: -0.0000

Data Index: 479182 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2146. Min Act: -0.0000

Data Index: 706311 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2100. Min Act: 0.0000

Data Index: 134510 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2108. Min Act: 0.0000

Data Index: 669815 (C4 (Web Text))

Max Activating Token Index: 544