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

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

Neuron 2858 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.4418. Min Act: -0.0001

Data Index: 777404 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3539. Min Act: -0.0001

Data Index: 786361 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3410. Min Act: -0.0001

Data Index: 483885 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3310. Min Act: -0.0001

Data Index: 504904 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3118. Min Act: -0.0001

Data Index: 1154606 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3057. Min Act: -0.0000

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2829. Min Act: -0.0001

Data Index: 1238912 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2801. Min Act: -0.0001

Data Index: 551179 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2762. Min Act: -0.0000

Data Index: 687408 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1322428 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2780. Min Act: -0.0001

Data Index: 682395 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2671. Min Act: -0.0001

Data Index: 946698 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2765. Min Act: -0.0000

Data Index: 719435 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2753. Min Act: -0.0001

Data Index: 629781 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2641. Min Act: -0.0000

Data Index: 667589 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1215074 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2724. Min Act: -0.0001

Data Index: 282250 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2613. Min Act: -0.0001

Data Index: 884006 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1000295 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.2696. Min Act: -0.0001

Data Index: 557228 (C4 (Web Text))

Max Activating Token Index: 615