Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1725 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0004

Data Index: 573213 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0725. Min Act: -0.0004

Data Index: 1447816 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0696. Min Act: -0.0004

Data Index: 620108 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0697. Min Act: -0.0004

Data Index: 615608 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0679. Min Act: -0.0004

Data Index: 1587193 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0677. Min Act: -0.0004

Data Index: 3467 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0626. Min Act: -0.0004

Data Index: 1522330 (Python Code)

Max Activating Token Index: 51

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0518. Min Act: -0.0004

Data Index: 1293135 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0512. Min Act: -0.0004

Data Index: 1491957 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0509. Min Act: -0.0004

Data Index: 1556449 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0520. Min Act: -0.0004

Data Index: 1484457 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0496. Min Act: -0.0004

Data Index: 1417030 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0479. Min Act: -0.0004

Data Index: 1553195 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0474. Min Act: -0.0004

Data Index: 532738 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0471. Min Act: -0.0004

Data Index: 1220499 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0471. Min Act: -0.0004

Data Index: 91368 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0466. Min Act: -0.0004

Data Index: 891775 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0459. Min Act: -0.0004

Data Index: 1338453 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0457. Min Act: -0.0004

Data Index: 1550720 (Python Code)

Max Activating Token Index: 881

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0445. Min Act: -0.0004

Data Index: 105677 (C4 (Web Text))

Max Activating Token Index: 267