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

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

Neuron 3801 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.4035. Min Act: -0.0001

Data Index: 1483923 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.4003. Min Act: -0.0001

Data Index: 1511259 (Python Code)

Max Activating Token Index: 424

Text #2

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1582719 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3010. Min Act: -0.0001

Data Index: 1378161 (Python Code)

Max Activating Token Index: 174

Text #4

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3775. Min Act: -0.0001

Data Index: 1438328 (Python Code)

Max Activating Token Index: 449

Text #5

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3685. Min Act: -0.0001

Data Index: 1531276 (Python Code)

Max Activating Token Index: 527

Text #6

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3057. Min Act: -0.0001

Data Index: 1432664 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2330. Min Act: -0.0001

Data Index: 1532226 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3077. Min Act: -0.0001

Data Index: 1621812 (Python Code)

Max Activating Token Index: 975

Text #9

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2996. Min Act: -0.0001

Data Index: 1499575 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3581. Min Act: -0.0000

Data Index: 1534336 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2458. Min Act: -0.0001

Data Index: 1545288 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2091. Min Act: -0.0001

Data Index: 1379251 (Python Code)

Max Activating Token Index: 876

Text #13

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2488. Min Act: -0.0001

Data Index: 1465746 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2216. Min Act: -0.0001

Data Index: 1394118 (Python Code)

Max Activating Token Index: 568

Text #15

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1420373 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1256. Min Act: -0.0001

Data Index: 1541457 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1438. Min Act: -0.0001

Data Index: 1548178 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1587084 (Python Code)

Max Activating Token Index: 383

Text #19

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1647801 (Python Code)

Max Activating Token Index: 841