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

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

Neuron 1030 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: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0001

Data Index: 715696 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0602. Min Act: -0.0001

Data Index: 734792 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0563. Min Act: -0.0001

Data Index: 489384 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1583627 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0515. Min Act: -0.0002

Data Index: 402013 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1233965 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1011772 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0482. Min Act: -0.0002

Data Index: 778245 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0477. Min Act: -0.0001

Data Index: 717794 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0477. Min Act: -0.0001

Data Index: 336964 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1029247 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1121537 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0447. Min Act: -0.0001

Data Index: 469693 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0475. Min Act: -0.0001

Data Index: 222678 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1491860 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1132155 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0456. Min Act: -0.0002

Data Index: 805171 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0455. Min Act: -0.0001

Data Index: 238367 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0454. Min Act: -0.0002

Data Index: 182543 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0472. Min Act: -0.0001

Data Index: 67722 (C4 (Web Text))

Max Activating Token Index: 153