Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0003

Data Index: 621724 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5110. Min Act: -0.0003

Data Index: 1263221 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4810. Min Act: -0.0003

Data Index: 921901 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4551. Min Act: -0.0003

Data Index: 1185575 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3469. Min Act: -0.0003

Data Index: 365923 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4839. Min Act: -0.0003

Data Index: 806927 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4585. Min Act: -0.0003

Data Index: 652291 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4409. Min Act: -0.0003

Data Index: 786388 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4636. Min Act: -0.0003

Data Index: 229989 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3950. Min Act: -0.0003

Data Index: 1311431 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4457. Min Act: -0.0003

Data Index: 447150 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4303. Min Act: -0.0003

Data Index: 576186 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4348. Min Act: -0.0003

Data Index: 904676 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4321. Min Act: -0.0003

Data Index: 1000994 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4334. Min Act: -0.0003

Data Index: 88919 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4184. Min Act: -0.0003

Data Index: 419467 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4146. Min Act: -0.0003

Data Index: 1073017 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4320. Min Act: -0.0003

Data Index: 1197325 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4394. Min Act: -0.0003

Data Index: 653149 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3863. Min Act: -0.0003

Data Index: 18271 (C4 (Web Text))

Max Activating Token Index: 149