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

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

Neuron 3646 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: 1.5477. Min Range: -1.5477

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1652896 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1381133 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1437968 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1530978 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1593373 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1440661 (Python Code)

Max Activating Token Index: 323

Text #6

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1649292 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1458669 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1360817 (Python Code)

Max Activating Token Index: 719

Text #9

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1389764 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.2626. Min Act: -0.0000

Data Index: 1429959 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1569128 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1444838 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1493583 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1393036 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1510682 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1637370 (Python Code)

Max Activating Token Index: 685

Text #17

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1513141 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1485978 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.2958. Min Act: -0.0000

Data Index: 1556109 (Python Code)

Max Activating Token Index: 467