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

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

Neuron 3072 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: 1.0374. Min Range: -1.0374

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1476643 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9108. Min Act: -0.0001

Data Index: 1578073 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1507864 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1437370 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7449. Min Act: -0.0000

Data Index: 275716 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1490453 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7430. Min Act: -0.0001

Data Index: 1621621 (Python Code)

Max Activating Token Index: 637

Text #7

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1079428 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1387381 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1291735 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6783. Min Act: -0.0000

Data Index: 249917 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1503259 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6489. Min Act: -0.0000

Data Index: 209744 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1147883 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.5615. Min Act: -0.0000

Data Index: 214872 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.5258. Min Act: -0.0000

Data Index: 669809 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6157. Min Act: -0.0000

Data Index: 711400 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6213. Min Act: -0.0000

Data Index: 282150 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.5767. Min Act: -0.0000

Data Index: 975459 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.5026. Min Act: -0.0000

Data Index: 166442 (C4 (Web Text))

Max Activating Token Index: 423