Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3096 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.5110. Min Act: -0.0002

Data Index: 330117 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.3801. Min Act: -0.0002

Data Index: 300222 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.3232. Min Act: -0.0002

Data Index: 919601 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.3049. Min Act: -0.0002

Data Index: 250311 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.3215. Min Act: -0.0002

Data Index: 626469 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2890. Min Act: -0.0002

Data Index: 655514 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2747. Min Act: -0.0002

Data Index: 554570 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2782. Min Act: -0.0002

Data Index: 1029073 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2799. Min Act: -0.0002

Data Index: 1244366 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2812. Min Act: -0.0002

Data Index: 129871 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2529. Min Act: -0.0003

Data Index: 474250 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2590. Min Act: -0.0003

Data Index: 770103 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2336. Min Act: -0.0002

Data Index: 1344311 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.2167. Min Act: -0.0002

Data Index: 1022680 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.1868. Min Act: -0.0002

Data Index: 488735 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.1898. Min Act: -0.0003

Data Index: 565694 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.1852. Min Act: -0.0002

Data Index: 1137064 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.1961. Min Act: -0.0002

Data Index: 124310 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.1770. Min Act: -0.0002

Data Index: 504276 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.1673. Min Act: -0.0003

Data Index: 464455 (C4 (Web Text))

Max Activating Token Index: 985