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

Dataset: The Pile

Neuron 3887 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: 0.8700. Min Range: -0.8700

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1386411 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1271335 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1199921 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7960. Min Act: -0.0000

Data Index: 719284 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1321296 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1169734 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8256. Min Act: -0.0000

Data Index: 230172 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1041349 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7836. Min Act: -0.0000

Data Index: 888656 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1353160 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1632108 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7791. Min Act: -0.0000

Data Index: 585661 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7279. Min Act: -0.0000

Data Index: 947790 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7662. Min Act: -0.0000

Data Index: 607261 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7076. Min Act: -0.0000

Data Index: 821371 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7225. Min Act: -0.0000

Data Index: 879628 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1193746 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6956. Min Act: -0.0000

Data Index: 404457 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7550. Min Act: -0.0000

Data Index: 425312 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6964. Min Act: -0.0000

Data Index: 486377 (The Pile)

Max Activating Token Index: 166