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

Dataset: The Pile

Neuron 2528 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: 0.2784. Min Range: -0.2784

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1147178 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1007429 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2784. Min Act: -0.0000

Data Index: 632753 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1417335 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1701509 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1311712 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2341. Min Act: -0.0000

Data Index: 2642 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1962640 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1952605 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2536. Min Act: -0.0000

Data Index: 168474 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2513. Min Act: -0.0000

Data Index: 358282 (The Pile)

Max Activating Token Index: 801

Text #11

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2498. Min Act: -0.0000

Data Index: 355971 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1722869 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1195939 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1072185 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2304. Min Act: -0.0000

Data Index: 423406 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1499075 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2303. Min Act: -0.0000

Data Index: 322969 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1789014 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1580678 (The Pile)

Max Activating Token Index: 124