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

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

Neuron 3680 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.2094. Min Act: -0.0000

Data Index: 539229 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9435. Min Act: -0.0000

Data Index: 974101 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.6686. Min Act: -0.0000

Data Index: 575275 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0448. Min Act: -0.0000

Data Index: 301313 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.8943. Min Act: -0.0000

Data Index: 965844 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.8275. Min Act: -0.0000

Data Index: 443254 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0211. Min Act: -0.0000

Data Index: 368007 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.6407. Min Act: -0.0000

Data Index: 320553 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.7826. Min Act: -0.0000

Data Index: 550578 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.6130. Min Act: -0.0000

Data Index: 924763 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.7563. Min Act: -0.0000

Data Index: 836380 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.5930. Min Act: -0.0000

Data Index: 106708 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.5034. Min Act: -0.0000

Data Index: 965901 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.5213. Min Act: -0.0000

Data Index: 443976 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.4726. Min Act: -0.0000

Data Index: 1107306 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.6284. Min Act: -0.0000

Data Index: 1202912 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.7344. Min Act: -0.0000

Data Index: 234414 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.4695. Min Act: -0.0000

Data Index: 526409 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.4878. Min Act: -0.0000

Data Index: 198740 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.3992. Min Act: -0.0000

Data Index: 930955 (C4 (Web Text))

Max Activating Token Index: 356