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

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

Neuron 1867 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.5605. Min Act: -0.0000

Data Index: 689074 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.7620. Min Act: -0.0000

Data Index: 57949 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.5273. Min Act: -0.0000

Data Index: 462149 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.3301. Min Act: -0.0000

Data Index: 429843 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.4355. Min Act: -0.0000

Data Index: 1162923 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.4550. Min Act: -0.0000

Data Index: 707844 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.2576. Min Act: -0.0000

Data Index: 1086063 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.3141. Min Act: -0.0000

Data Index: 310748 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.2875. Min Act: -0.0000

Data Index: 919932 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.2795. Min Act: -0.0000

Data Index: 390471 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.0851. Min Act: -0.0000

Data Index: 1469065 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.0248. Min Act: -0.0000

Data Index: 621347 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.0189. Min Act: -0.0000

Data Index: 1221993 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 3.7620. Min Range: -3.7620

Max Act: 2.8248. Min Act: -0.0000

Data Index: 1346007 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 3.7620. Min Range: -3.7620

Max Act: 2.7939. Min Act: -0.0000

Data Index: 597658 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 3.7620. Min Range: -3.7620

Max Act: 3.2223. Min Act: -0.0000

Data Index: 1067227 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 3.7620. Min Range: -3.7620

Max Act: 2.7594. Min Act: -0.0000

Data Index: 78826 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 3.7620. Min Range: -3.7620

Max Act: 2.9905. Min Act: -0.0000

Data Index: 1051008 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.7620. Min Range: -3.7620

Max Act: 2.8694. Min Act: -0.0000

Data Index: 940087 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 3.7620. Min Range: -3.7620

Max Act: 2.8030. Min Act: -0.0000

Data Index: 570854 (C4 (Web Text))

Max Activating Token Index: 259