Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0607. Min Range: -1.0607

Max Act: 1.0607. Min Act: -0.0001

Data Index: 1334879 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1265594 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.9368. Min Act: -0.0001

Data Index: 562379 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7903. Min Act: -0.0001

Data Index: 488322 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8431. Min Act: -0.0001

Data Index: 1084016 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8098. Min Act: -0.0001

Data Index: 279626 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8474. Min Act: -0.0001

Data Index: 948495 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8145. Min Act: -0.0001

Data Index: 1382338 (Python Code)

Max Activating Token Index: 360

Text #8

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8101. Min Act: -0.0001

Data Index: 419951 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1363037 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7887. Min Act: -0.0001

Data Index: 1534055 (Python Code)

Max Activating Token Index: 449

Text #11

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1421619 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8111. Min Act: -0.0001

Data Index: 144339 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7681. Min Act: -0.0001

Data Index: 1461504 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7903. Min Act: -0.0000

Data Index: 440380 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7908. Min Act: -0.0001

Data Index: 142812 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1133643 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7383. Min Act: -0.0001

Data Index: 1390717 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1643256 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7989. Min Act: -0.0000

Data Index: 382578 (C4 (Web Text))

Max Activating Token Index: 28