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

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

Neuron 2282 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0446. Min Range: -3.0446

Max Act: 3.0446. Min Act: -0.0000

Data Index: 1632681 (Python Code)

Max Activating Token Index: 865

Text #1

Max Range: 3.0446. Min Range: -3.0446

Max Act: 2.8103. Min Act: -0.0000

Data Index: 1521211 (Python Code)

Max Activating Token Index: 376

Text #2

Max Range: 3.0446. Min Range: -3.0446

Max Act: 2.4167. Min Act: -0.0000

Data Index: 1581331 (Python Code)

Max Activating Token Index: 589

Text #3

Max Range: 3.0446. Min Range: -3.0446

Max Act: 2.2589. Min Act: -0.0000

Data Index: 1519041 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 3.0446. Min Range: -3.0446

Max Act: 2.3180. Min Act: -0.0000

Data Index: 1525771 (Python Code)

Max Activating Token Index: 507

Text #5

Max Range: 3.0446. Min Range: -3.0446

Max Act: 2.2235. Min Act: -0.0000

Data Index: 1538913 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 3.0446. Min Range: -3.0446

Max Act: 2.0464. Min Act: -0.0000

Data Index: 1422486 (Python Code)

Max Activating Token Index: 347

Text #7

Max Range: 3.0446. Min Range: -3.0446

Max Act: 2.0368. Min Act: -0.0000

Data Index: 1618058 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.7532. Min Act: -0.0000

Data Index: 1565054 (Python Code)

Max Activating Token Index: 769

Text #9

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1379837 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.8259. Min Act: -0.0000

Data Index: 1602624 (Python Code)

Max Activating Token Index: 283

Text #11

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.8087. Min Act: -0.0000

Data Index: 1606576 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1531217 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.8697. Min Act: -0.0000

Data Index: 1623130 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1644126 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.7469. Min Act: -0.0000

Data Index: 1626529 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1613991 (Python Code)

Max Activating Token Index: 977

Text #17

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1394500 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1633143 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 3.0446. Min Range: -3.0446

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1611066 (Python Code)

Max Activating Token Index: 716