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

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

Neuron 2639 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.3207. Min Act: -0.0001

Data Index: 1314882 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.3596. Min Act: -0.0000

Data Index: 370080 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.2740. Min Act: -0.0001

Data Index: 863543 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.2471. Min Act: -0.0001

Data Index: 87577 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.2123. Min Act: -0.0001

Data Index: 1105203 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0216. Min Act: -0.0001

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.1138. Min Act: -0.0001

Data Index: 650794 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0271. Min Act: -0.0001

Data Index: 522586 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0068. Min Act: -0.0001

Data Index: 942048 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9586. Min Act: -0.0001

Data Index: 1112123 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9830. Min Act: -0.0001

Data Index: 845457 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9146. Min Act: -0.0001

Data Index: 1344170 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9074. Min Act: -0.0001

Data Index: 816217 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.8985. Min Act: -0.0001

Data Index: 637789 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9639. Min Act: -0.0001

Data Index: 351106 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9130. Min Act: -0.0001

Data Index: 118425 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9048. Min Act: -0.0001

Data Index: 17371 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.8231. Min Act: -0.0001

Data Index: 515632 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9006. Min Act: -0.0001

Data Index: 239024 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.8900. Min Act: -0.0001

Data Index: 65716 (C4 (Web Text))

Max Activating Token Index: 472