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

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

Neuron 4028 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: 0.3171. Min Range: -0.3171

Max Act: 0.3171. Min Act: -0.0001

Data Index: 184786 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1022137 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1069263 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2591. Min Act: -0.0001

Data Index: 261652 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2605. Min Act: -0.0001

Data Index: 1344767 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2284. Min Act: -0.0001

Data Index: 955937 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2146. Min Act: -0.0001

Data Index: 322408 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2107. Min Act: -0.0001

Data Index: 191972 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1981. Min Act: -0.0001

Data Index: 289407 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1323543 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1833. Min Act: -0.0001

Data Index: 399720 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1654. Min Act: -0.0001

Data Index: 708488 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1945. Min Act: -0.0001

Data Index: 297298 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1165795 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1808. Min Act: -0.0001

Data Index: 94981 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1800. Min Act: -0.0001

Data Index: 845748 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1647. Min Act: -0.0001

Data Index: 948294 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1892. Min Act: -0.0001

Data Index: 998708 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1750. Min Act: -0.0001

Data Index: 415474 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1151813 (C4 (Web Text))

Max Activating Token Index: 376