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

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

Neuron 1075 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: 0.0883. Min Range: -0.0883

Max Act: 0.0883. Min Act: -0.0001

Data Index: 939825 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0645. Min Act: -0.0001

Data Index: 987454 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0699. Min Act: -0.0002

Data Index: 598996 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0677. Min Act: -0.0002

Data Index: 863470 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0700. Min Act: -0.0002

Data Index: 283914 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1581577 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1470336 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0638. Min Act: -0.0001

Data Index: 167291 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0699. Min Act: -0.0001

Data Index: 805177 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1421855 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0637. Min Act: -0.0002

Data Index: 810443 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1512925 (Python Code)

Max Activating Token Index: 787

Text #12

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0652. Min Act: -0.0002

Data Index: 765401 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0627. Min Act: -0.0001

Data Index: 68087 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1456051 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0641. Min Act: -0.0002

Data Index: 805054 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1134805 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0713. Min Act: -0.0002

Data Index: 518334 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0662. Min Act: -0.0001

Data Index: 198109 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0652. Min Act: -0.0001

Data Index: 123437 (C4 (Web Text))

Max Activating Token Index: 28