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

Dataset: The Pile

Neuron 2212 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.6747. Min Act: -0.0000

Data Index: 1186190 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5026. Min Act: -0.0000

Data Index: 1930612 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4831. Min Act: -0.0000

Data Index: 396928 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.6351. Min Act: -0.0000

Data Index: 753525 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.1520. Min Act: -0.0000

Data Index: 1136309 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5968. Min Act: -0.0000

Data Index: 1415116 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4144. Min Act: -0.0000

Data Index: 985929 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.2033. Min Act: -0.0000

Data Index: 1835867 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.1990. Min Act: -0.0000

Data Index: 708662 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4417. Min Act: -0.0000

Data Index: 738306 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.1803. Min Act: -0.0000

Data Index: 1104314 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.3236. Min Act: -0.0000

Data Index: 59538 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.2825. Min Act: -0.0000

Data Index: 1672372 (The Pile)

Max Activating Token Index: 230

Text #13

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4442. Min Act: -0.0000

Data Index: 326277 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.6262. Min Act: -0.0000

Data Index: 1870671 (The Pile)

Max Activating Token Index: 163

Text #15

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.1603. Min Act: -0.0000

Data Index: 915898 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.1401. Min Act: -0.0000

Data Index: 1137213 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.2831. Min Act: -0.0000

Data Index: 1601772 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.2876. Min Act: -0.0000

Data Index: 319295 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.1061. Min Act: -0.0000

Data Index: 413725 (The Pile)

Max Activating Token Index: 293