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

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

Neuron 3881 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: 0.8407. Min Range: -0.8407

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1360458 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1448765 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1544317 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1544934 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1424814 (Python Code)

Max Activating Token Index: 221

Text #5

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1595300 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1442018 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1610488 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1392919 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1470435 (Python Code)

Max Activating Token Index: 921

Text #10

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.4102. Min Act: -0.0000

Data Index: 454759 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1538130 (Python Code)

Max Activating Token Index: 730

Text #12

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1383549 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1650381 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1299742 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1633799 (Python Code)

Max Activating Token Index: 624

Text #16

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1586453 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1488646 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1591600 (Python Code)

Max Activating Token Index: 640

Text #19

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1650927 (Python Code)

Max Activating Token Index: 703