Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2455 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.0286. Min Range: -5.0286

Max Act: 5.0286. Min Act: -0.0001

Data Index: 1569818 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.9706. Min Act: -0.0001

Data Index: 1637919 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7343. Min Act: -0.0001

Data Index: 1396039 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.5698. Min Act: -0.0001

Data Index: 1544444 (Python Code)

Max Activating Token Index: 491

Text #4

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.5662. Min Act: -0.0001

Data Index: 1546411 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.3873. Min Act: -0.0001

Data Index: 1458337 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.3231. Min Act: -0.0001

Data Index: 1450987 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.2605. Min Act: -0.0001

Data Index: 1585260 (Python Code)

Max Activating Token Index: 145

Text #8

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.3891. Min Act: -0.0001

Data Index: 1415702 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.2181. Min Act: -0.0001

Data Index: 1479074 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.3937. Min Act: -0.0001

Data Index: 1491903 (Python Code)

Max Activating Token Index: 818

Text #11

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.3122. Min Act: -0.0001

Data Index: 1656140 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.3079. Min Act: -0.0001

Data Index: 1409952 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 5.0286. Min Range: -5.0286

Max Act: 3.8933. Min Act: -0.0001

Data Index: 1434302 (Python Code)

Max Activating Token Index: 939

Text #14

Max Range: 5.0286. Min Range: -5.0286

Max Act: 3.8860. Min Act: -0.0001

Data Index: 1576065 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.1603. Min Act: -0.0001

Data Index: 1380182 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 5.0286. Min Range: -5.0286

Max Act: 3.9948. Min Act: -0.0001

Data Index: 1635954 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.1097. Min Act: -0.0001

Data Index: 1415347 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.3055. Min Act: -0.0001

Data Index: 1388324 (Python Code)

Max Activating Token Index: 667

Text #19

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.2708. Min Act: -0.0001

Data Index: 1364974 (Python Code)

Max Activating Token Index: 31