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

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

Neuron 4519 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1075032 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.1034. Min Act: -0.0000

Data Index: 255600 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1119884 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1354390 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0772. Min Act: -0.0000

Data Index: 670722 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0674. Min Act: -0.0000

Data Index: 1155770 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0845. Min Act: -0.0000

Data Index: 442757 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0629. Min Act: -0.0000

Data Index: 537517 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0619. Min Act: -0.0000

Data Index: 695371 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1598972 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1510425 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1559231 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1408318 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0610. Min Act: -0.0000

Data Index: 680572 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1360837 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1324416 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0563. Min Act: -0.0000

Data Index: 1612846 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1553618 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1430544 (Python Code)

Max Activating Token Index: 425

Text #19

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1498391 (Python Code)

Max Activating Token Index: 129