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

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

Neuron 2350 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4864. Min Act: -0.0001

Data Index: 576363 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2546. Min Act: -0.0001

Data Index: 854582 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2619. Min Act: -0.0001

Data Index: 939787 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2393. Min Act: -0.0001

Data Index: 911244 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2094. Min Act: -0.0001

Data Index: 534736 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2539. Min Act: -0.0001

Data Index: 638697 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2281. Min Act: -0.0001

Data Index: 428398 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1170796 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2211. Min Act: -0.0001

Data Index: 883722 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2181. Min Act: -0.0001

Data Index: 402812 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2162. Min Act: -0.0001

Data Index: 944234 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2070. Min Act: -0.0001

Data Index: 1032194 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2173. Min Act: -0.0001

Data Index: 257393 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1173521 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2019. Min Act: -0.0001

Data Index: 518075 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2053. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2007. Min Act: -0.0001

Data Index: 886012 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.2061. Min Act: -0.0001

Data Index: 464929 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.1873. Min Act: -0.0001

Data Index: 233307 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.1946. Min Act: -0.0001

Data Index: 129855 (C4 (Web Text))

Max Activating Token Index: 635