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

Dataset: The Pile

Neuron 3786 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: 0.5332. Min Range: -0.5332

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1884983 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3836. Min Act: -0.0000

Data Index: 803442 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3956. Min Act: -0.0000

Data Index: 816734 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1067384 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4616. Min Act: -0.0000

Data Index: 783018 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1695880 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1535618 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2699. Min Act: -0.0000

Data Index: 400781 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1969244 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3777. Min Act: -0.0000

Data Index: 173113 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1946991 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1940141 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3223. Min Act: -0.0000

Data Index: 256361 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3345. Min Act: -0.0000

Data Index: 412138 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3455. Min Act: -0.0000

Data Index: 815142 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3103. Min Act: -0.0000

Data Index: 327287 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1494169 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3046. Min Act: -0.0000

Data Index: 809696 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1542096 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3289. Min Act: -0.0000

Data Index: 526525 (The Pile)

Max Activating Token Index: 553