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

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

Neuron 5452 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.8772. Min Act: -0.0000

Data Index: 1439028 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.5787. Min Act: -0.0000

Data Index: 1471822 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.5479. Min Act: -0.0001

Data Index: 1517596 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.3648. Min Act: -0.0000

Data Index: 1575557 (Python Code)

Max Activating Token Index: 643

Text #4

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.3609. Min Act: -0.0001

Data Index: 1406387 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4259. Min Act: -0.0001

Data Index: 1545851 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.1161. Min Act: -0.0001

Data Index: 1530803 (Python Code)

Max Activating Token Index: 300

Text #7

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.2623. Min Act: -0.0000

Data Index: 1581815 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.2598. Min Act: -0.0001

Data Index: 1564272 (Python Code)

Max Activating Token Index: 839

Text #9

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.0860. Min Act: -0.0000

Data Index: 1622875 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.0264. Min Act: -0.0001

Data Index: 1483709 (Python Code)

Max Activating Token Index: 193

Text #11

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.2873. Min Act: -0.0001

Data Index: 1510686 (Python Code)

Max Activating Token Index: 429

Text #12

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.1083. Min Act: -0.0000

Data Index: 1415828 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.0726. Min Act: -0.0001

Data Index: 1429994 (Python Code)

Max Activating Token Index: 723

Text #14

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.0654. Min Act: -0.0001

Data Index: 1362766 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.0505. Min Act: -0.0000

Data Index: 1611570 (Python Code)

Max Activating Token Index: 79

Text #16

Max Range: 3.8772. Min Range: -3.8772

Max Act: 2.9245. Min Act: -0.0000

Data Index: 1471122 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 3.8772. Min Range: -3.8772

Max Act: 2.9231. Min Act: -0.0001

Data Index: 1475987 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 3.8772. Min Range: -3.8772

Max Act: 2.9227. Min Act: -0.0000

Data Index: 1637399 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 3.8772. Min Range: -3.8772

Max Act: 2.9093. Min Act: -0.0001

Data Index: 1470890 (Python Code)

Max Activating Token Index: 173