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

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

Neuron 3079 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2299. Min Range: -1.2299

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1563837 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1465601 (Python Code)

Max Activating Token Index: 563

Text #2

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1407417 (Python Code)

Max Activating Token Index: 522

Text #3

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1526985 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1362282 (Python Code)

Max Activating Token Index: 1007

Text #5

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1600132 (Python Code)

Max Activating Token Index: 543

Text #6

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1388219 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6594. Min Act: -0.0000

Data Index: 357735 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1526477 (Python Code)

Max Activating Token Index: 678

Text #9

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1393286 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1438425 (Python Code)

Max Activating Token Index: 1011

Text #11

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1625936 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1456554 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1501901 (Python Code)

Max Activating Token Index: 711

Text #14

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1586298 (Python Code)

Max Activating Token Index: 367

Text #15

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1385282 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1627915 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.5810. Min Act: -0.0000

Data Index: 571483 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1449721 (Python Code)

Max Activating Token Index: 408

Text #19

Max Range: 1.2299. Min Range: -1.2299

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1542439 (Python Code)

Max Activating Token Index: 513