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

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

Neuron 4804 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.8446. Min Act: -0.0002

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.8064. Min Act: -0.0002

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.8052. Min Act: -0.0002

Data Index: 1318008 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.7416. Min Act: -0.0002

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.6539. Min Act: -0.0002

Data Index: 707072 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.5986. Min Act: -0.0002

Data Index: 16939 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.5473. Min Act: -0.0002

Data Index: 480098 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.5035. Min Act: -0.0002

Data Index: 128092 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.5038. Min Act: -0.0002

Data Index: 655346 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.4941. Min Act: -0.0002

Data Index: 1173719 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.4480. Min Act: -0.0002

Data Index: 44054 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.4395. Min Act: -0.0002

Data Index: 645320 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.4294. Min Act: -0.0002

Data Index: 315948 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.4041. Min Act: -0.0002

Data Index: 329769 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.4209. Min Act: -0.0002

Data Index: 968516 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.3821. Min Act: -0.0002

Data Index: 470856 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.4092. Min Act: -0.0002

Data Index: 1048127 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.3966. Min Act: -0.0002

Data Index: 410633 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.3667. Min Act: -0.0002

Data Index: 389882 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.8446. Min Range: -1.8446

Max Act: 1.3412. Min Act: -0.0002

Data Index: 1028696 (C4 (Web Text))

Max Activating Token Index: 989