Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3921 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4509. Min Act: -0.0003

Data Index: 824761 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4558. Min Act: -0.0003

Data Index: 220013 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4232. Min Act: -0.0002

Data Index: 1015044 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4246. Min Act: -0.0003

Data Index: 12833 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4165. Min Act: -0.0003

Data Index: 602547 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4157. Min Act: -0.0003

Data Index: 637637 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4093. Min Act: -0.0003

Data Index: 864616 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4060. Min Act: -0.0003

Data Index: 425291 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4030. Min Act: -0.0002

Data Index: 559121 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4005. Min Act: -0.0003

Data Index: 206898 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3990. Min Act: -0.0003

Data Index: 162412 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3932. Min Act: -0.0003

Data Index: 1281146 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3888. Min Act: -0.0003

Data Index: 708425 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3769. Min Act: -0.0003

Data Index: 1132201 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3731. Min Act: -0.0003

Data Index: 1240340 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3718. Min Act: -0.0003

Data Index: 1170501 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3561. Min Act: -0.0003

Data Index: 176895 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3683. Min Act: -0.0003

Data Index: 353946 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3803. Min Act: -0.0003

Data Index: 739118 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3672. Min Act: -0.0003

Data Index: 412220 (C4 (Web Text))

Max Activating Token Index: 470