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

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

Neuron 4798 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1391360 (Python Code)

Max Activating Token Index: 682

Text #1

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4892. Min Act: -0.0000

Data Index: 778077 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1423855 (Python Code)

Max Activating Token Index: 478

Text #3

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4435. Min Act: -0.0000

Data Index: 962950 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1390762 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1412087 (Python Code)

Max Activating Token Index: 139

Text #6

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4159. Min Act: -0.0000

Data Index: 553271 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1547331 (Python Code)

Max Activating Token Index: 387

Text #8

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4133. Min Act: -0.0000

Data Index: 389890 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1049260 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4056. Min Act: -0.0000

Data Index: 203354 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4013. Min Act: -0.0000

Data Index: 933479 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4120. Min Act: -0.0000

Data Index: 972367 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1423930 (Python Code)

Max Activating Token Index: 434

Text #14

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1576117 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1583667 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3734. Min Act: -0.0000

Data Index: 489333 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1128791 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1548830 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3905. Min Act: -0.0000

Data Index: 230429 (C4 (Web Text))

Max Activating Token Index: 615