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

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

Neuron 4401 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0684. Min Range: -4.0684

Max Act: 4.0684. Min Act: -0.0000

Data Index: 1368545 (Python Code)

Max Activating Token Index: 474

Text #1

Max Range: 4.0684. Min Range: -4.0684

Max Act: 4.0046. Min Act: -0.0000

Data Index: 1468710 (Python Code)

Max Activating Token Index: 638

Text #2

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9890. Min Act: -0.0000

Data Index: 1389056 (Python Code)

Max Activating Token Index: 490

Text #3

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9516. Min Act: -0.0000

Data Index: 1611719 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 4.0684. Min Range: -4.0684

Max Act: 4.0093. Min Act: -0.0000

Data Index: 1416947 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.8025. Min Act: -0.0000

Data Index: 1630604 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9515. Min Act: -0.0000

Data Index: 1508695 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.8954. Min Act: -0.0000

Data Index: 1586264 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.6947. Min Act: -0.0000

Data Index: 1370320 (Python Code)

Max Activating Token Index: 965

Text #9

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.5295. Min Act: -0.0000

Data Index: 1639051 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.6392. Min Act: -0.0000

Data Index: 1519691 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.5484. Min Act: -0.0000

Data Index: 1635967 (Python Code)

Max Activating Token Index: 488

Text #12

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.5332. Min Act: -0.0000

Data Index: 1561675 (Python Code)

Max Activating Token Index: 746

Text #13

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.3764. Min Act: -0.0000

Data Index: 1386065 (Python Code)

Max Activating Token Index: 523

Text #14

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.5194. Min Act: -0.0000

Data Index: 1509534 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.5092. Min Act: -0.0000

Data Index: 1567475 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.5029. Min Act: -0.0000

Data Index: 1472984 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.2303. Min Act: -0.0000

Data Index: 1448334 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.5174. Min Act: -0.0000

Data Index: 1436057 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.3581. Min Act: -0.0000

Data Index: 1518158 (Python Code)

Max Activating Token Index: 720