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

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

Neuron 2160 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: 0.7696. Min Range: -0.7696

Max Act: 0.7696. Min Act: -0.0000

Data Index: 203914 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6298. Min Act: -0.0001

Data Index: 164961 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1209946 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1250484 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5191. Min Act: -0.0001

Data Index: 1458958 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5203. Min Act: -0.0001

Data Index: 1395367 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4529. Min Act: -0.0000

Data Index: 334527 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1353813 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4633. Min Act: -0.0000

Data Index: 375603 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4445. Min Act: -0.0000

Data Index: 838225 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4438. Min Act: -0.0000

Data Index: 851687 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1010813 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.3996. Min Act: -0.0001

Data Index: 36725 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4112. Min Act: -0.0001

Data Index: 996988 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.3925. Min Act: -0.0001

Data Index: 109503 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1459369 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.3830. Min Act: -0.0001

Data Index: 1447149 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.3768. Min Act: -0.0001

Data Index: 275685 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1008398 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.3744. Min Act: -0.0000

Data Index: 762495 (C4 (Web Text))

Max Activating Token Index: 72