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

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

Neuron 3630 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.8455. Min Act: -0.0000

Data Index: 595565 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.7938. Min Act: -0.0000

Data Index: 584354 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.7620. Min Act: 0.0000

Data Index: 884105 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1315437 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6597. Min Act: -0.0000

Data Index: 125053 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6202. Min Act: -0.0000

Data Index: 965535 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6050. Min Act: -0.0000

Data Index: 227550 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6157. Min Act: -0.0000

Data Index: 475646 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5952. Min Act: -0.0000

Data Index: 385293 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6012. Min Act: -0.0000

Data Index: 357053 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5719. Min Act: -0.0000

Data Index: 819801 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.6311. Min Act: -0.0000

Data Index: 823785 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5983. Min Act: -0.0000

Data Index: 165026 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5319. Min Act: -0.0000

Data Index: 101239 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5472. Min Act: -0.0000

Data Index: 567278 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5384. Min Act: -0.0000

Data Index: 754498 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1281924 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1184907 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.4755. Min Act: -0.0000

Data Index: 573768 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.8455. Min Range: -0.8455

Max Act: 0.5389. Min Act: -0.0000

Data Index: 772069 (C4 (Web Text))

Max Activating Token Index: 639