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

Dataset: The Pile

Neuron 349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1023888 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1517563 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.2022. Min Act: -0.0000

Data Index: 1622146 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.1757. Min Act: -0.0000

Data Index: 581193 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.1022. Min Act: -0.0000

Data Index: 457285 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.1236. Min Act: -0.0000

Data Index: 1476411 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0726. Min Act: -0.0000

Data Index: 389156 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1649519 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0001. Min Act: -0.0000

Data Index: 860440 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0254. Min Act: -0.0000

Data Index: 358325 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0143. Min Act: -0.0000

Data Index: 120713 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9976. Min Act: -0.0000

Data Index: 110249 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1208666 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1801000 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1292147 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9545. Min Act: -0.0000

Data Index: 919388 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1452163 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1925219 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1385613 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1096417 (The Pile)

Max Activating Token Index: 198