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

Dataset: The Pile

Neuron 5057 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1480990 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1211314 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9412. Min Act: -0.0000

Data Index: 620113 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9394. Min Act: -0.0000

Data Index: 268688 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1278732 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9385. Min Act: -0.0000

Data Index: 139877 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9323. Min Act: -0.0000

Data Index: 961811 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1026409 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1771621 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8690. Min Act: -0.0000

Data Index: 602196 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1994134 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1669682 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1307064 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1425658 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8699. Min Act: -0.0000

Data Index: 649286 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1905115 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1610547 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1840205 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1393979 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8605. Min Act: -0.0000

Data Index: 301158 (The Pile)

Max Activating Token Index: 846