Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1607 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1373647 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1373503 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1404885 (Python Code)

Max Activating Token Index: 490

Text #3

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1557795 (Python Code)

Max Activating Token Index: 173

Text #4

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1388240 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1620479 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1536884 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6650. Min Act: 0.0000

Data Index: 1422016 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1415671 (Python Code)

Max Activating Token Index: 345

Text #9

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1625651 (Python Code)

Max Activating Token Index: 511

Text #10

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1444022 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1374691 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1513767 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1568801 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6405. Min Act: 0.0000

Data Index: 1607936 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1418130 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1446782 (Python Code)

Max Activating Token Index: 436

Text #17

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1438545 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5816. Min Act: -0.0000

Data Index: 246962 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1446701 (Python Code)

Max Activating Token Index: 207