Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2525 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0761. Min Act: -0.0001

Data Index: 339368 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0759. Min Act: -0.0001

Data Index: 415916 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1095498 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1350233 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0603. Min Act: -0.0001

Data Index: 56452 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0585. Min Act: -0.0001

Data Index: 284955 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0585. Min Act: -0.0001

Data Index: 873146 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0592. Min Act: -0.0001

Data Index: 965085 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1342688 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0583. Min Act: -0.0001

Data Index: 715026 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0569. Min Act: -0.0001

Data Index: 800817 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1180456 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0530. Min Act: -0.0001

Data Index: 154747 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1355798 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0583. Min Act: -0.0001

Data Index: 804202 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0540. Min Act: -0.0001

Data Index: 847811 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0511. Min Act: -0.0001

Data Index: 450188 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1149010 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0536. Min Act: -0.0001

Data Index: 85081 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1209641 (C4 (Web Text))

Max Activating Token Index: 656