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

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

Neuron 710 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0553. Min Act: -0.0003

Data Index: 112794 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0527. Min Act: -0.0004

Data Index: 105321 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0540. Min Act: -0.0003

Data Index: 866372 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0475. Min Act: -0.0004

Data Index: 1047183 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0502. Min Act: -0.0003

Data Index: 512748 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0461. Min Act: -0.0003

Data Index: 175755 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0476. Min Act: -0.0003

Data Index: 689103 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1085245 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0464. Min Act: -0.0003

Data Index: 610085 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0482. Min Act: -0.0003

Data Index: 89312 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1319528 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1243784 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1295461 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0508. Min Act: -0.0003

Data Index: 297284 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0467. Min Act: -0.0003

Data Index: 633883 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0466. Min Act: -0.0003

Data Index: 392429 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0463. Min Act: -0.0003

Data Index: 628447 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0461. Min Act: -0.0003

Data Index: 420471 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0474. Min Act: -0.0003

Data Index: 869559 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0465. Min Act: -0.0003

Data Index: 776626 (C4 (Web Text))

Max Activating Token Index: 751