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

Dataset: The Pile

Neuron 584 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: 0.4240. Min Range: -0.4240

Max Act: 0.4240. Min Act: -0.0000

Data Index: 97137 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3198. Min Act: -0.0000

Data Index: 906493 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2916. Min Act: -0.0000

Data Index: 349112 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2300. Min Act: -0.0000

Data Index: 985921 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1220649 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1011455 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2332. Min Act: -0.0000

Data Index: 606807 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1912569 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2390. Min Act: -0.0000

Data Index: 753547 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1228923 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1092177 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1354390 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1710280 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2261. Min Act: -0.0000

Data Index: 653865 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2058. Min Act: -0.0000

Data Index: 202696 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1260078 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2024. Min Act: -0.0000

Data Index: 559521 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1514284 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2117. Min Act: -0.0000

Data Index: 490394 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.1849. Min Act: -0.0000

Data Index: 719110 (The Pile)

Max Activating Token Index: 901