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

Dataset: The Pile

Neuron 910 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1272345 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3309. Min Act: -0.0000

Data Index: 506571 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3079. Min Act: -0.0000

Data Index: 519392 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1445433 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2866. Min Act: -0.0000

Data Index: 709054 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1515700 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2797. Min Act: -0.0000

Data Index: 381432 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2760. Min Act: -0.0000

Data Index: 413960 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1894678 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1497334 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1527138 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1938332 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2517. Min Act: -0.0000

Data Index: 68498 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1356084 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2507. Min Act: -0.0000

Data Index: 393388 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1059138 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1178347 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1187924 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1879231 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1152204 (The Pile)

Max Activating Token Index: 523