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

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

Neuron 1992 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1479. Min Range: -1.1479

Max Act: 1.1479. Min Act: -0.0001

Data Index: 355856 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8401. Min Act: -0.0001

Data Index: 223816 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8957. Min Act: -0.0001

Data Index: 527182 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7978. Min Act: -0.0001

Data Index: 165925 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8138. Min Act: -0.0001

Data Index: 767825 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7372. Min Act: -0.0001

Data Index: 804597 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1178763 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7542. Min Act: -0.0001

Data Index: 317287 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7747. Min Act: -0.0000

Data Index: 887262 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7219. Min Act: -0.0001

Data Index: 302211 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.6730. Min Act: -0.0001

Data Index: 674290 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7304. Min Act: -0.0001

Data Index: 559912 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.6401. Min Act: -0.0000

Data Index: 16427 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.6994. Min Act: -0.0001

Data Index: 719562 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.6739. Min Act: -0.0001

Data Index: 622280 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.6740. Min Act: -0.0001

Data Index: 523588 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.6954. Min Act: -0.0001

Data Index: 402602 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7192. Min Act: -0.0001

Data Index: 581613 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7152. Min Act: -0.0001

Data Index: 904943 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1087630 (C4 (Web Text))

Max Activating Token Index: 490