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

Dataset: The Pile

Neuron 3498 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: 1.5685. Min Range: -1.5685

Max Act: 1.5685. Min Act: 0.0000

Data Index: 1080549 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1989021 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.3025. Min Act: -0.0000

Data Index: 681870 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1472485 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2723. Min Act: -0.0000

Data Index: 195908 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1764776 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1196403 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1594022 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1396. Min Act: -0.0000

Data Index: 585138 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0637. Min Act: -0.0000

Data Index: 309208 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0232. Min Act: -0.0000

Data Index: 534124 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0139. Min Act: -0.0000

Data Index: 778466 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1474453 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.9864. Min Act: -0.0000

Data Index: 617065 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1013665 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.9322. Min Act: -0.0000

Data Index: 776654 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1967211 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.9122. Min Act: 0.0000

Data Index: 281259 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1821675 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 1.5685. Min Range: -1.5685

Max Act: 0.8032. Min Act: -0.0000

Data Index: 631958 (The Pile)

Max Activating Token Index: 959