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

Dataset: The Pile

Neuron 2476 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: 0.7424. Min Range: -0.7424

Max Act: 0.7169. Min Act: -0.0000

Data Index: 293086 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1048639 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1948239 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1025410 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6534. Min Act: 0.0001

Data Index: 576725 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6489. Min Act: -0.0000

Data Index: 715056 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1849494 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6333. Min Act: 0.0001

Data Index: 848691 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6532. Min Act: 0.0000

Data Index: 300399 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5705. Min Act: -0.0000

Data Index: 450110 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1380190 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1423800 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6149. Min Act: 0.0001

Data Index: 644105 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5918. Min Act: -0.0000

Data Index: 583130 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5885. Min Act: -0.0000

Data Index: 24876 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5725. Min Act: -0.0000

Data Index: 138303 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5967. Min Act: 0.0001

Data Index: 1504189 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5917. Min Act: -0.0000

Data Index: 602413 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5726. Min Act: -0.0000

Data Index: 511996 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1401276 (The Pile)

Max Activating Token Index: 796