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

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

Neuron 2838 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.7646. Min Act: -0.0001

Data Index: 381400 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.6041. Min Act: -0.0001

Data Index: 210062 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.4767. Min Act: -0.0001

Data Index: 1099387 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.5567. Min Act: -0.0001

Data Index: 239341 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.4101. Min Act: -0.0001

Data Index: 779269 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3723. Min Act: -0.0001

Data Index: 1547182 (Python Code)

Max Activating Token Index: 139

Text #6

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3927. Min Act: -0.0001

Data Index: 936883 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.4267. Min Act: -0.0001

Data Index: 392567 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3833. Min Act: -0.0001

Data Index: 192315 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3851. Min Act: -0.0001

Data Index: 378310 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3760. Min Act: -0.0001

Data Index: 1257071 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3716. Min Act: -0.0001

Data Index: 1333623 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3973. Min Act: -0.0001

Data Index: 768801 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.1979. Min Act: -0.0001

Data Index: 1469063 (Python Code)

Max Activating Token Index: 707

Text #14

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3319. Min Act: -0.0001

Data Index: 638126 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2953. Min Act: -0.0001

Data Index: 973748 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3730. Min Act: -0.0001

Data Index: 739861 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3218. Min Act: -0.0001

Data Index: 149373 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3568. Min Act: -0.0001

Data Index: 629092 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2605. Min Act: -0.0001

Data Index: 566496 (C4 (Web Text))

Max Activating Token Index: 617