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

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

Neuron 5500 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: 1.1549. Min Range: -1.1549

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1217969 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1290569 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1074618 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8015. Min Act: -0.0000

Data Index: 828058 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1311178 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.7762. Min Act: -0.0000

Data Index: 181139 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.7380. Min Act: -0.0000

Data Index: 236532 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.6692. Min Act: -0.0000

Data Index: 962495 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.6346. Min Act: -0.0000

Data Index: 937784 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.7063. Min Act: -0.0000

Data Index: 569590 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.6662. Min Act: -0.0000

Data Index: 647075 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1149963 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.6192. Min Act: -0.0000

Data Index: 360517 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1303400 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.5870. Min Act: -0.0000

Data Index: 642665 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.6057. Min Act: -0.0000

Data Index: 915518 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.5907. Min Act: -0.0000

Data Index: 885853 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.5990. Min Act: -0.0000

Data Index: 319675 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.5976. Min Act: -0.0000

Data Index: 966786 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.5762. Min Act: -0.0000

Data Index: 965948 (C4 (Web Text))

Max Activating Token Index: 748