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

Dataset: The Pile

Neuron 1512 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: 0.3117. Min Range: -0.3117

Max Act: 0.3117. Min Act: -0.0000

Data Index: 981643 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1605025 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2772. Min Act: -0.0000

Data Index: 630180 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2538. Min Act: -0.0000

Data Index: 97668 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1470551 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2708. Min Act: -0.0000

Data Index: 776128 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1032619 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.3036. Min Act: -0.0000

Data Index: 660585 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1499745 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1843929 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2540. Min Act: -0.0000

Data Index: 77474 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2594. Min Act: -0.0000

Data Index: 683592 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1802145 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1966007 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1190874 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1391112 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1183690 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2689. Min Act: -0.0000

Data Index: 580417 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1413381 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1443590 (The Pile)

Max Activating Token Index: 994