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

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

Neuron 3954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9048. Min Act: -0.0001

Data Index: 1540671 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 1.0350. Min Range: -1.0350

Max Act: 1.0350. Min Act: -0.0000

Data Index: 521388 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9097. Min Act: -0.0000

Data Index: 172012 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9171. Min Act: -0.0001

Data Index: 1656275 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1152577 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8083. Min Act: -0.0001

Data Index: 1527628 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.7558. Min Act: -0.0000

Data Index: 349402 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.7462. Min Act: -0.0000

Data Index: 71582 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1225111 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1405140 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.7293. Min Act: -0.0001

Data Index: 1537713 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.7438. Min Act: -0.0000

Data Index: 162958 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.6847. Min Act: -0.0000

Data Index: 911106 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1124740 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.7097. Min Act: -0.0000

Data Index: 122021 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.6477. Min Act: -0.0001

Data Index: 792409 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.6463. Min Act: -0.0000

Data Index: 67554 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.5276. Min Act: -0.0000

Data Index: 546416 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1550241 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1082990 (C4 (Web Text))

Max Activating Token Index: 641