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

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

Neuron 241 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.6273. Min Act: -0.0000

Data Index: 987117 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1188323 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.3799. Min Act: -0.0000

Data Index: 1296634 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.2313. Min Act: 0.0002

Data Index: 803707 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1011956 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.2496. Min Act: -0.0000

Data Index: 442243 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.0321. Min Act: -0.0000

Data Index: 560708 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.0790. Min Act: -0.0000

Data Index: 397748 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.0615. Min Act: -0.0000

Data Index: 185574 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.9675. Min Act: -0.0000

Data Index: 523864 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.9997. Min Act: -0.0000

Data Index: 279454 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1088786 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.9749. Min Act: 0.0000

Data Index: 1357526 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 1.6273. Min Range: -1.6273

Max Act: 1.0224. Min Act: -0.0000

Data Index: 190412 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.8768. Min Act: -0.0000

Data Index: 676148 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.9839. Min Act: -0.0000

Data Index: 959880 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1226118 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1196561 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.8351. Min Act: -0.0000

Data Index: 776545 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 1.6273. Min Range: -1.6273

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1080817 (C4 (Web Text))

Max Activating Token Index: 755