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

Dataset: The Pile

Neuron 5083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3746. Min Act: -0.0000

Data Index: 791296 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.4362. Min Act: -0.0000

Data Index: 1208356 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2542. Min Act: -0.0000

Data Index: 807105 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2251. Min Act: -0.0000

Data Index: 1228241 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2770. Min Act: -0.0000

Data Index: 978190 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3149. Min Act: -0.0000

Data Index: 39825 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2379. Min Act: -0.0000

Data Index: 1982032 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1901290 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2977. Min Act: -0.0000

Data Index: 1995565 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1767559 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2638. Min Act: -0.0000

Data Index: 909569 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2403. Min Act: -0.0001

Data Index: 1531364 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1727917 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1101716 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1146333 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.1519. Min Act: -0.0000

Data Index: 51071 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1782433 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1368144 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1711106 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1081774 (The Pile)

Max Activating Token Index: 51