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

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

Neuron 568 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1550980 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1360417 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1504019 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1638837 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1362312 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1585569 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1636778 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1403052 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1411559 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1534918 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1508329 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1538758 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2741. Min Act: -0.0000

Data Index: 1601096 (Python Code)

Max Activating Token Index: 476

Text #13

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2553. Min Act: -0.0000

Data Index: 1498336 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1607079 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1365860 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1406815 (Python Code)

Max Activating Token Index: 343

Text #17

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1592089 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1556263 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 1.4947. Min Range: -1.4947

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1607983 (Python Code)

Max Activating Token Index: 385