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

Dataset: The Pile

Neuron 2061 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.8198. Min Act: -0.0000

Data Index: 967490 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1116763 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4151. Min Act: -0.0000

Data Index: 11560 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4827. Min Act: -0.0000

Data Index: 1466381 (The Pile)

Max Activating Token Index: 800

Text #4

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1536118 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1105249 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3244. Min Act: -0.0000

Data Index: 258640 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3880. Min Act: -0.0000

Data Index: 116954 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3064. Min Act: -0.0000

Data Index: 683008 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4464. Min Act: -0.0000

Data Index: 1724711 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3357. Min Act: -0.0000

Data Index: 747016 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4240. Min Act: -0.0000

Data Index: 233164 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4826. Min Act: -0.0000

Data Index: 736051 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3859. Min Act: -0.0000

Data Index: 708066 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3990. Min Act: -0.0000

Data Index: 1505268 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2358. Min Act: -0.0000

Data Index: 387084 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1471539 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2555. Min Act: -0.0000

Data Index: 628530 (The Pile)

Max Activating Token Index: 844

Text #18

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2673. Min Act: -0.0000

Data Index: 1830900 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1124051 (The Pile)

Max Activating Token Index: 684