Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 497 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0557. Min Act: -0.0001

Data Index: 882415 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1024648 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0523. Min Act: -0.0001

Data Index: 806555 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1069729 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1100530 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1221846 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1530065 (Python Code)

Max Activating Token Index: 861

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0435. Min Act: -0.0001

Data Index: 399406 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1131733 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0499. Min Act: -0.0002

Data Index: 959088 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0465. Min Act: -0.0002

Data Index: 3460 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0473. Min Act: -0.0002

Data Index: 391724 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1544123 (Python Code)

Max Activating Token Index: 796

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1135590 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0508. Min Act: -0.0001

Data Index: 859304 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0435. Min Act: -0.0001

Data Index: 969958 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0450. Min Act: -0.0001

Data Index: 464007 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0484. Min Act: -0.0002

Data Index: 600206 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1320903 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1214098 (C4 (Web Text))

Max Activating Token Index: 877