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

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

Neuron 3014 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8625. Min Act: -0.0000

Data Index: 888229 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8575. Min Act: -0.0000

Data Index: 543576 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1034721 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8333. Min Act: -0.0000

Data Index: 813037 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1337634 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7795. Min Act: -0.0000

Data Index: 906466 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1335704 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8348. Min Act: -0.0000

Data Index: 680744 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7847. Min Act: -0.0000

Data Index: 388472 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8221. Min Act: -0.0000

Data Index: 150616 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1315986 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7317. Min Act: -0.0000

Data Index: 561309 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7825. Min Act: -0.0000

Data Index: 346056 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1124117 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1014099 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7490. Min Act: -0.0000

Data Index: 878837 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1327559 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1329445 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7431. Min Act: -0.0000

Data Index: 526589 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.7718. Min Act: -0.0000

Data Index: 263072 (C4 (Web Text))

Max Activating Token Index: 99