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

Dataset: The Pile

Neuron 2232 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: 1.7263. Min Range: -1.7263

Max Act: 1.7263. Min Act: -0.0000

Data Index: 1624443 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5351. Min Act: -0.0000

Data Index: 1130261 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.6956. Min Act: -0.0000

Data Index: 1704100 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5703. Min Act: -0.0000

Data Index: 1071253 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4629. Min Act: -0.0000

Data Index: 485464 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5355. Min Act: -0.0000

Data Index: 930515 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1073083 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4982. Min Act: -0.0000

Data Index: 378432 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3289. Min Act: -0.0000

Data Index: 1128877 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3836. Min Act: -0.0000

Data Index: 162327 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3182. Min Act: -0.0000

Data Index: 874508 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1266270 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1510641 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3674. Min Act: -0.0000

Data Index: 1874441 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2873. Min Act: -0.0000

Data Index: 457520 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2091. Min Act: -0.0000

Data Index: 181951 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2077. Min Act: -0.0000

Data Index: 450065 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2497. Min Act: -0.0000

Data Index: 306395 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3321. Min Act: -0.0000

Data Index: 305717 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1750585 (The Pile)

Max Activating Token Index: 130