Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2327 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.4252. Min Act: -0.0000

Data Index: 888399 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3655. Min Act: 0.0000

Data Index: 889771 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3514. Min Act: -0.0000

Data Index: 938415 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1524236 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3148. Min Act: 0.0000

Data Index: 1541852 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1452847 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3022. Min Act: -0.0000

Data Index: 546948 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1249785 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1872836 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1127259 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2921. Min Act: -0.0000

Data Index: 895735 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2872. Min Act: -0.0000

Data Index: 969499 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2835. Min Act: -0.0000

Data Index: 171782 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1910948 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2796. Min Act: -0.0000

Data Index: 494328 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1412950 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2766. Min Act: -0.0000

Data Index: 547448 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2687. Min Act: -0.0000

Data Index: 609747 (The Pile)

Max Activating Token Index: 674

Text #18

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1557384 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2595. Min Act: -0.0000

Data Index: 607833 (The Pile)

Max Activating Token Index: 244