Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1842 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.5108. Min Act: -0.0006

Data Index: 766365 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4894. Min Act: -0.0006

Data Index: 1050471 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4409. Min Act: -0.0006

Data Index: 41258 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4410. Min Act: -0.0006

Data Index: 658327 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4639. Min Act: -0.0006

Data Index: 534445 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4154. Min Act: -0.0006

Data Index: 431247 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4754. Min Act: -0.0006

Data Index: 1196664 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4207. Min Act: -0.0006

Data Index: 1241798 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4499. Min Act: -0.0006

Data Index: 97268 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4741. Min Act: -0.0006

Data Index: 221784 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4531. Min Act: -0.0006

Data Index: 354764 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4366. Min Act: -0.0006

Data Index: 833615 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4201. Min Act: -0.0006

Data Index: 757695 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4338. Min Act: -0.0006

Data Index: 1184766 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4187. Min Act: -0.0006

Data Index: 1015161 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4961. Min Act: -0.0006

Data Index: 928575 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4154. Min Act: -0.0006

Data Index: 1155767 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3954. Min Act: -0.0006

Data Index: 104302 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4512. Min Act: -0.0006

Data Index: 699977 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4354. Min Act: -0.0006

Data Index: 687760 (C4 (Web Text))

Max Activating Token Index: 418