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

Dataset: The Pile

Neuron 4783 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2970. Min Act: -0.0000

Data Index: 159488 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2926. Min Act: -0.0000

Data Index: 341699 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1027095 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2697. Min Act: -0.0000

Data Index: 16964 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1203439 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1116287 (The Pile)

Max Activating Token Index: 713

Text #6

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1605606 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2728. Min Act: -0.0000

Data Index: 753753 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1032712 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2658. Min Act: -0.0000

Data Index: 297611 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2465. Min Act: -0.0000

Data Index: 957637 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1422562 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1199718 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2445. Min Act: -0.0000

Data Index: 132124 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1033335 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1289854 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1961572 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1188728 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1781466 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1094031 (The Pile)

Max Activating Token Index: 250