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

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

Neuron 592 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2320. Min Range: -2.2320

Max Act: 2.2320. Min Act: -0.0000

Data Index: 427467 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.9441. Min Act: -0.0000

Data Index: 538799 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 2.2320. Min Range: -2.2320

Max Act: 2.0090. Min Act: -0.0000

Data Index: 687860 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 2.2320. Min Range: -2.2320

Max Act: 2.0088. Min Act: -0.0000

Data Index: 922970 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.9225. Min Act: -0.0000

Data Index: 645341 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.8346. Min Act: -0.0000

Data Index: 278268 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.9386. Min Act: -0.0000

Data Index: 768152 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.9130. Min Act: -0.0001

Data Index: 20154 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.9018. Min Act: -0.0000

Data Index: 340117 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.7702. Min Act: -0.0000

Data Index: 799219 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.7728. Min Act: -0.0000

Data Index: 485829 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.6722. Min Act: -0.0000

Data Index: 416365 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.7496. Min Act: -0.0000

Data Index: 33627 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.8436. Min Act: -0.0000

Data Index: 915500 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.7320. Min Act: -0.0000

Data Index: 561012 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.7088. Min Act: -0.0000

Data Index: 667707 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.7100. Min Act: -0.0000

Data Index: 1354439 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.6048. Min Act: -0.0001

Data Index: 1336127 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1004457 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 2.2320. Min Range: -2.2320

Max Act: 1.8540. Min Act: -0.0000

Data Index: 801285 (C4 (Web Text))

Max Activating Token Index: 147