Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 648 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.5999. Min Act: -0.0000

Data Index: 127909 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3542. Min Act: -0.0000

Data Index: 949948 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1264721 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1310004 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2380. Min Act: -0.0000

Data Index: 130910 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3068. Min Act: -0.0001

Data Index: 622131 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2435. Min Act: -0.0001

Data Index: 802961 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2347. Min Act: -0.0001

Data Index: 1260134 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3147. Min Act: -0.0000

Data Index: 764097 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2130. Min Act: -0.0000

Data Index: 804170 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2659. Min Act: -0.0000

Data Index: 551272 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.1980. Min Act: -0.0000

Data Index: 371263 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.1522. Min Act: -0.0000

Data Index: 940573 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1299843 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.5999. Min Range: -1.5999

Max Act: 0.9741. Min Act: -0.0000

Data Index: 877018 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.5999. Min Range: -1.5999

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1107616 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.1417. Min Act: -0.0001

Data Index: 1073420 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.0362. Min Act: -0.0000

Data Index: 139947 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.0276. Min Act: -0.0001

Data Index: 293114 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.0567. Min Act: -0.0000

Data Index: 53937 (C4 (Web Text))

Max Activating Token Index: 401