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

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

Neuron 3458 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4070. Min Act: -0.0001

Data Index: 1051929 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4288. Min Act: -0.0000

Data Index: 563086 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4224. Min Act: -0.0001

Data Index: 1497478 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4115. Min Act: -0.0001

Data Index: 1235224 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1468530 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1251945 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1550033 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1627034 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1391431 (Python Code)

Max Activating Token Index: 364

Text #9

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3452. Min Act: -0.0000

Data Index: 399792 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4127. Min Act: -0.0000

Data Index: 827451 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3716. Min Act: -0.0001

Data Index: 976284 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1470104 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3697. Min Act: -0.0001

Data Index: 1510969 (Python Code)

Max Activating Token Index: 441

Text #14

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3588. Min Act: -0.0000

Data Index: 430268 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1542480 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3689. Min Act: -0.0001

Data Index: 959902 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3493. Min Act: -0.0001

Data Index: 1552232 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1451324 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1443948 (Python Code)

Max Activating Token Index: 527