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

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

Neuron 4471 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9123. Min Range: -4.9123

Max Act: 4.9123. Min Act: -0.0000

Data Index: 822074 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 4.9123. Min Range: -4.9123

Max Act: 4.3081. Min Act: -0.0000

Data Index: 769488 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 4.9123. Min Range: -4.9123

Max Act: 4.0581. Min Act: -0.0000

Data Index: 672099 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 4.9123. Min Range: -4.9123

Max Act: 4.0219. Min Act: -0.0000

Data Index: 1111598 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.6145. Min Act: -0.0000

Data Index: 25693 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.5920. Min Act: -0.0000

Data Index: 1558263 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.4425. Min Act: -0.0000

Data Index: 236195 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.4062. Min Act: -0.0000

Data Index: 487284 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.3858. Min Act: -0.0000

Data Index: 301998 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.2540. Min Act: -0.0000

Data Index: 534761 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.2248. Min Act: -0.0000

Data Index: 548453 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.2157. Min Act: -0.0000

Data Index: 1321278 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.0203. Min Act: -0.0000

Data Index: 117689 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.1530. Min Act: -0.0000

Data Index: 1292704 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.1299. Min Act: -0.0000

Data Index: 643102 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.1181. Min Act: -0.0000

Data Index: 1265603 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.1208. Min Act: -0.0000

Data Index: 272817 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.2719. Min Act: -0.0000

Data Index: 730482 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 4.9123. Min Range: -4.9123

Max Act: 2.7883. Min Act: -0.0000

Data Index: 388965 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 4.9123. Min Range: -4.9123

Max Act: 3.0509. Min Act: -0.0000

Data Index: 1237446 (C4 (Web Text))

Max Activating Token Index: 615