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

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

Neuron 2887 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2696. Min Act: -0.0000

Data Index: 883121 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2099. Min Act: -0.0000

Data Index: 471744 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2015. Min Act: -0.0000

Data Index: 652221 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1961. Min Act: -0.0000

Data Index: 9189 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1213469 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1984. Min Act: -0.0000

Data Index: 536557 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2097. Min Act: -0.0000

Data Index: 668324 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1969. Min Act: -0.0000

Data Index: 731679 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1223237 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1823. Min Act: -0.0000

Data Index: 715119 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1933. Min Act: -0.0000

Data Index: 150626 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1797. Min Act: -0.0000

Data Index: 479225 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1822. Min Act: -0.0000

Data Index: 714796 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1779. Min Act: -0.0000

Data Index: 346747 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1097910 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1768. Min Act: -0.0000

Data Index: 511508 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1779. Min Act: -0.0000

Data Index: 895056 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1786. Min Act: -0.0000

Data Index: 307471 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1061018 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1703. Min Act: -0.0000

Data Index: 288111 (C4 (Web Text))

Max Activating Token Index: 858