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

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

Neuron 1 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1243985 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.5074. Min Act: -0.0000

Data Index: 916652 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4390. Min Act: -0.0000

Data Index: 172769 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4205. Min Act: -0.0000

Data Index: 275839 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3956. Min Act: -0.0000

Data Index: 257270 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4081. Min Act: -0.0000

Data Index: 851231 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4044. Min Act: -0.0000

Data Index: 786148 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3666. Min Act: -0.0000

Data Index: 869352 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4042. Min Act: -0.0000

Data Index: 585510 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4238. Min Act: -0.0001

Data Index: 141902 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1143019 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3936. Min Act: -0.0000

Data Index: 810490 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1260100 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3935. Min Act: -0.0000

Data Index: 745679 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1323631 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3656. Min Act: -0.0000

Data Index: 98427 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3700. Min Act: -0.0000

Data Index: 719410 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3397. Min Act: -0.0000

Data Index: 580027 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3657. Min Act: -0.0000

Data Index: 469899 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3398. Min Act: -0.0000

Data Index: 295214 (C4 (Web Text))

Max Activating Token Index: 268