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

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

Neuron 1647 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.7312. Min Act: -0.0001

Data Index: 379776 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.5089. Min Act: -0.0001

Data Index: 633582 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.4272. Min Act: -0.0001

Data Index: 592990 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.4079. Min Act: -0.0001

Data Index: 1243407 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.4484. Min Act: -0.0001

Data Index: 959852 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.2714. Min Act: -0.0001

Data Index: 1141300 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.2002. Min Act: -0.0001

Data Index: 862416 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.0452. Min Act: -0.0001

Data Index: 843031 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.2205. Min Act: -0.0001

Data Index: 822747 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.0934. Min Act: -0.0001

Data Index: 33814 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1307. Min Act: -0.0001

Data Index: 394639 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1491. Min Act: -0.0001

Data Index: 794340 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1642. Min Act: -0.0001

Data Index: 131388 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1371. Min Act: -0.0001

Data Index: 975976 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.0433. Min Act: -0.0001

Data Index: 869960 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1097. Min Act: -0.0001

Data Index: 1328073 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1742. Min Act: -0.0001

Data Index: 494088 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1044. Min Act: -0.0001

Data Index: 400786 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1396. Min Act: -0.0001

Data Index: 946285 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1301. Min Act: -0.0001

Data Index: 944678 (C4 (Web Text))

Max Activating Token Index: 975