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

Dataset: The Pile

Neuron 4589 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: 9.7924. Min Range: -9.7924

Max Act: 9.6989. Min Act: -0.0000

Data Index: 786232 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 9.7924. Min Range: -9.7924

Max Act: 9.7924. Min Act: -0.0000

Data Index: 1370479 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 9.7924. Min Range: -9.7924

Max Act: 9.7742. Min Act: -0.0000

Data Index: 121682 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 9.7924. Min Range: -9.7924

Max Act: 9.3381. Min Act: -0.0000

Data Index: 1428691 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 9.7924. Min Range: -9.7924

Max Act: 9.4717. Min Act: -0.0000

Data Index: 974484 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 9.7924. Min Range: -9.7924

Max Act: 9.2523. Min Act: -0.0000

Data Index: 1942560 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.6353. Min Act: -0.0000

Data Index: 1212924 (The Pile)

Max Activating Token Index: 366

Text #7

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.8633. Min Act: -0.0000

Data Index: 314996 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.7456. Min Act: -0.0000

Data Index: 919391 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.5233. Min Act: -0.0000

Data Index: 1330604 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.4911. Min Act: -0.0000

Data Index: 1064396 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.7850. Min Act: -0.0000

Data Index: 426623 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.7659. Min Act: -0.0000

Data Index: 1400862 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.1463. Min Act: -0.0000

Data Index: 290828 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.4655. Min Act: -0.0000

Data Index: 160773 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.5034. Min Act: -0.0000

Data Index: 983572 (The Pile)

Max Activating Token Index: 578

Text #16

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.8519. Min Act: -0.0000

Data Index: 940713 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.1423. Min Act: -0.0000

Data Index: 1272199 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.2916. Min Act: -0.0000

Data Index: 1406772 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 9.7924. Min Range: -9.7924

Max Act: 8.4238. Min Act: -0.0000

Data Index: 1823076 (The Pile)

Max Activating Token Index: 448