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

Dataset: The Pile

Neuron 1146 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: 0.2926. Min Range: -0.2926

Max Act: 0.2768. Min Act: -0.0000

Data Index: 755027 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2709. Min Act: -0.0000

Data Index: 58897 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2657. Min Act: -0.0000

Data Index: 590241 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1844082 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1067681 (The Pile)

Max Activating Token Index: 320

Text #5

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1721649 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2668. Min Act: -0.0000

Data Index: 255976 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2750. Min Act: -0.0000

Data Index: 851905 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1685250 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1743583 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2443. Min Act: -0.0000

Data Index: 290050 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1218994 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1862701 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1141310 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2468. Min Act: -0.0000

Data Index: 359928 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1146179 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2417. Min Act: -0.0000

Data Index: 316710 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1533812 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1175103 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1469903 (The Pile)

Max Activating Token Index: 313