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

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

Neuron 2384 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1569. Min Act: -0.0000

Data Index: 91540 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1534. Min Act: -0.0000

Data Index: 335161 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1433. Min Act: -0.0001

Data Index: 332965 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1425. Min Act: -0.0001

Data Index: 132851 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1223. Min Act: -0.0001

Data Index: 389984 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1254. Min Act: -0.0001

Data Index: 438527 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1242979 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1152. Min Act: -0.0000

Data Index: 100141 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1141. Min Act: -0.0001

Data Index: 930968 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1316. Min Act: -0.0001

Data Index: 178026 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1025758 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1499475 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1408209 (Python Code)

Max Activating Token Index: 657

Text #13

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1109. Min Act: -0.0001

Data Index: 707422 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1016193 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1538816 (Python Code)

Max Activating Token Index: 345

Text #16

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1162. Min Act: -0.0001

Data Index: 288489 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1263256 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1223. Min Act: -0.0001

Data Index: 427620 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1185. Min Act: -0.0001

Data Index: 780543 (C4 (Web Text))

Max Activating Token Index: 217