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

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

Neuron 2068 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: 0.6485. Min Range: -0.6485

Max Act: 0.6245. Min Act: -0.0000

Data Index: 616510 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.6485. Min Act: -0.0000

Data Index: 772242 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5040. Min Act: -0.0001

Data Index: 163853 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1334306 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4507. Min Act: -0.0001

Data Index: 947921 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4716. Min Act: -0.0001

Data Index: 132923 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1095676 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4379. Min Act: -0.0000

Data Index: 150742 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4583. Min Act: -0.0000

Data Index: 609674 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1188718 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4348. Min Act: -0.0000

Data Index: 364619 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4668. Min Act: -0.0000

Data Index: 950446 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1270466 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4302. Min Act: -0.0000

Data Index: 893922 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1352053 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4593. Min Act: -0.0000

Data Index: 139112 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1036775 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4111. Min Act: -0.0001

Data Index: 575852 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1068830 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4086. Min Act: -0.0000

Data Index: 237459 (C4 (Web Text))

Max Activating Token Index: 492