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

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

Neuron 1473 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.6303. Min Act: -0.0000

Data Index: 1585149 (Python Code)

Max Activating Token Index: 840

Text #1

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4935. Min Act: -0.0000

Data Index: 1560988 (Python Code)

Max Activating Token Index: 625

Text #2

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.2006. Min Act: -0.0000

Data Index: 1475862 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.1633. Min Act: -0.0000

Data Index: 1574097 (Python Code)

Max Activating Token Index: 755

Text #4

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.2238. Min Act: -0.0000

Data Index: 1521332 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.9484. Min Act: -0.0000

Data Index: 1365561 (Python Code)

Max Activating Token Index: 923

Text #6

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.9182. Min Act: -0.0000

Data Index: 1640500 (Python Code)

Max Activating Token Index: 390

Text #7

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.8856. Min Act: -0.0000

Data Index: 1594159 (Python Code)

Max Activating Token Index: 486

Text #8

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1512610 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.8495. Min Act: -0.0000

Data Index: 1645100 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.8347. Min Act: -0.0000

Data Index: 1476205 (Python Code)

Max Activating Token Index: 694

Text #11

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.7465. Min Act: -0.0000

Data Index: 1528458 (Python Code)

Max Activating Token Index: 947

Text #12

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.7731. Min Act: -0.0000

Data Index: 1500554 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.7000. Min Act: -0.0000

Data Index: 1383171 (Python Code)

Max Activating Token Index: 414

Text #14

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.7877. Min Act: -0.0000

Data Index: 1502507 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.6832. Min Act: -0.0000

Data Index: 1455599 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.6391. Min Act: -0.0000

Data Index: 1543401 (Python Code)

Max Activating Token Index: 494

Text #17

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1513348 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.7188. Min Act: -0.0000

Data Index: 1643384 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 2.6303. Min Range: -2.6303

Max Act: 1.6236. Min Act: -0.0000

Data Index: 1369045 (Python Code)

Max Activating Token Index: 284