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

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

Neuron 89 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4984. Min Act: -0.0001

Data Index: 1525897 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.5916. Min Act: -0.0001

Data Index: 1547230 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.9657. Min Act: -0.0001

Data Index: 1562627 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.8740. Min Act: -0.0001

Data Index: 1507464 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.8971. Min Act: -0.0001

Data Index: 1554485 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.9168. Min Act: -0.0001

Data Index: 1442704 (Python Code)

Max Activating Token Index: 429

Text #6

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.8798. Min Act: -0.0001

Data Index: 1378185 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1606070 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1601099 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7776. Min Act: -0.0001

Data Index: 1478686 (Python Code)

Max Activating Token Index: 894

Text #10

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.8437. Min Act: -0.0001

Data Index: 1630583 (Python Code)

Max Activating Token Index: 1004

Text #11

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7813. Min Act: -0.0001

Data Index: 1410526 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7551. Min Act: -0.0001

Data Index: 1432748 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7241. Min Act: -0.0001

Data Index: 1565307 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7818. Min Act: -0.0001

Data Index: 1654693 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.6796. Min Act: -0.0001

Data Index: 1485884 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7441. Min Act: -0.0001

Data Index: 1385523 (Python Code)

Max Activating Token Index: 218

Text #17

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.6828. Min Act: -0.0001

Data Index: 1557147 (Python Code)

Max Activating Token Index: 710

Text #18

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7177. Min Act: -0.0001

Data Index: 953829 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.6925. Min Act: -0.0001

Data Index: 1592517 (Python Code)

Max Activating Token Index: 559