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

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

Neuron 1715 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: 1.9253. Min Range: -1.9253

Max Act: 1.9253. Min Act: -0.0000

Data Index: 854168 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.6565. Min Act: -0.0000

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.6232. Min Act: -0.0000

Data Index: 16164 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.4906. Min Act: -0.0000

Data Index: 881680 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.4410. Min Act: -0.0000

Data Index: 218361 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.4329. Min Act: -0.0000

Data Index: 748051 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.3416. Min Act: -0.0000

Data Index: 947611 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.3801. Min Act: -0.0000

Data Index: 704970 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.2635. Min Act: -0.0000

Data Index: 286829 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.2314. Min Act: -0.0000

Data Index: 251079 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.2997. Min Act: -0.0000

Data Index: 313356 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.3314. Min Act: -0.0000

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.3151. Min Act: -0.0000

Data Index: 813797 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.2839. Min Act: -0.0000

Data Index: 147615 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.2442. Min Act: -0.0000

Data Index: 285195 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.2825. Min Act: -0.0000

Data Index: 1102561 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.2517. Min Act: -0.0000

Data Index: 554792 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.1692. Min Act: -0.0000

Data Index: 475029 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.9253. Min Range: -1.9253

Max Act: 1.1847. Min Act: -0.0000

Data Index: 69841 (C4 (Web Text))

Max Activating Token Index: 194