Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5447. Min Act: -0.0000

Data Index: 95705 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.6065. Min Act: -0.0000

Data Index: 193750 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5480. Min Act: -0.0000

Data Index: 179893 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1223114 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5503. Min Act: -0.0000

Data Index: 875142 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4689. Min Act: -0.0000

Data Index: 328696 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.5234. Min Act: -0.0000

Data Index: 595717 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4752. Min Act: -0.0000

Data Index: 267517 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4696. Min Act: -0.0000

Data Index: 576760 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4994. Min Act: -0.0000

Data Index: 719965 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1300666 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1240769 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4468. Min Act: -0.0000

Data Index: 397657 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4713. Min Act: -0.0000

Data Index: 870109 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4559. Min Act: -0.0000

Data Index: 669151 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4703. Min Act: -0.0000

Data Index: 725350 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1218630 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4382. Min Act: -0.0000

Data Index: 78390 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4722. Min Act: -0.0000

Data Index: 925814 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.6065. Min Range: -0.6065

Max Act: 0.4321. Min Act: -0.0000

Data Index: 83640 (C4 (Web Text))

Max Activating Token Index: 354