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

Dataset: The Pile

Neuron 2057 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: 0.5629. Min Range: -0.5629

Max Act: 0.5629. Min Act: -0.0000

Data Index: 337447 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3806. Min Act: -0.0000

Data Index: 934655 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1679730 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3364. Min Act: -0.0000

Data Index: 414554 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3429. Min Act: -0.0000

Data Index: 891362 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3417. Min Act: -0.0000

Data Index: 531342 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1533209 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3348. Min Act: -0.0000

Data Index: 745660 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1948684 (The Pile)

Max Activating Token Index: 455

Text #9

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1040977 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1001253 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1498780 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1842235 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1309374 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1770562 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3198. Min Act: -0.0000

Data Index: 406584 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1387269 (The Pile)

Max Activating Token Index: 495

Text #17

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3153. Min Act: -0.0000

Data Index: 758937 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.2918. Min Act: -0.0000

Data Index: 485751 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1010724 (The Pile)

Max Activating Token Index: 370