Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 62 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.7508. Min Act: -0.0000

Data Index: 1389903 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.5848. Min Act: -0.0000

Data Index: 1437283 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.5325. Min Act: -0.0000

Data Index: 1533760 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.5772. Min Act: -0.0000

Data Index: 1388871 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.3595. Min Act: -0.0000

Data Index: 1512335 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.3714. Min Act: -0.0000

Data Index: 1426103 (Python Code)

Max Activating Token Index: 459

Text #6

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.2582. Min Act: -0.0000

Data Index: 1514798 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.3536. Min Act: -0.0000

Data Index: 1423968 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.2074. Min Act: -0.0000

Data Index: 1388371 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.1923. Min Act: -0.0000

Data Index: 1466819 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.0869. Min Act: -0.0000

Data Index: 1450471 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.1306. Min Act: -0.0000

Data Index: 1593454 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.1210. Min Act: -0.0000

Data Index: 1485760 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.2217. Min Act: -0.0000

Data Index: 1456451 (Python Code)

Max Activating Token Index: 726

Text #14

Max Range: 2.7508. Min Range: -2.7508

Max Act: 1.9078. Min Act: -0.0000

Data Index: 1431534 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.1976. Min Act: -0.0000

Data Index: 1363376 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.1041. Min Act: -0.0000

Data Index: 1583079 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.2054. Min Act: -0.0000

Data Index: 1423486 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 2.7508. Min Range: -2.7508

Max Act: 2.0044. Min Act: -0.0000

Data Index: 1543573 (Python Code)

Max Activating Token Index: 572

Text #19

Max Range: 2.7508. Min Range: -2.7508

Max Act: 1.8686. Min Act: -0.0000

Data Index: 1543589 (Python Code)

Max Activating Token Index: 739