Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.8169. Min Act: -0.0000

Data Index: 1266932 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.4970. Min Act: -0.0000

Data Index: 1115780 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.5678. Min Act: -0.0000

Data Index: 738472 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.3713. Min Act: -0.0000

Data Index: 87932 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.3628. Min Act: -0.0000

Data Index: 52405 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.4705. Min Act: -0.0000

Data Index: 641560 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.3512. Min Act: -0.0000

Data Index: 426563 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.4562. Min Act: -0.0000

Data Index: 1314704 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.1035. Min Act: -0.0000

Data Index: 1345808 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.3292. Min Act: -0.0000

Data Index: 665064 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.0873. Min Act: -0.0000

Data Index: 72870 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.1416. Min Act: -0.0000

Data Index: 124276 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.1626. Min Act: -0.0000

Data Index: 440073 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.3090. Min Act: -0.0000

Data Index: 205548 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.1551. Min Act: -0.0000

Data Index: 1215428 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.1373. Min Act: -0.0000

Data Index: 426399 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.1201. Min Act: -0.0000

Data Index: 41525 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.0186. Min Act: -0.0000

Data Index: 1052137 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.2333. Min Act: -0.0000

Data Index: 1307284 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 2.8169. Min Range: -2.8169

Max Act: 2.0093. Min Act: -0.0000

Data Index: 618282 (C4 (Web Text))

Max Activating Token Index: 199