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

Dataset: The Pile

Neuron 2676 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: 5.1347. Min Range: -5.1347

Max Act: 5.0838. Min Act: -0.0000

Data Index: 694784 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 5.1347. Min Range: -5.1347

Max Act: 5.1285. Min Act: -0.0000

Data Index: 181575 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 5.1347. Min Range: -5.1347

Max Act: 5.1347. Min Act: -0.0000

Data Index: 528927 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.8682. Min Act: -0.0000

Data Index: 1658571 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.9495. Min Act: -0.0000

Data Index: 821502 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.7449. Min Act: -0.0000

Data Index: 305259 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.9877. Min Act: -0.0000

Data Index: 337573 (The Pile)

Max Activating Token Index: 780

Text #7

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.6130. Min Act: -0.0000

Data Index: 188840 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.4123. Min Act: -0.0000

Data Index: 49245 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.6431. Min Act: -0.0000

Data Index: 539418 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.8111. Min Act: -0.0000

Data Index: 1876251 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.5998. Min Act: -0.0000

Data Index: 942517 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.5786. Min Act: -0.0000

Data Index: 1521317 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.2064. Min Act: -0.0000

Data Index: 127474 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.4341. Min Act: -0.0000

Data Index: 1907160 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.0639. Min Act: -0.0000

Data Index: 488830 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.2159. Min Act: -0.0000

Data Index: 1145263 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.1829. Min Act: -0.0000

Data Index: 704575 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 5.1347. Min Range: -5.1347

Max Act: 4.0346. Min Act: -0.0000

Data Index: 1978723 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 5.1347. Min Range: -5.1347

Max Act: 3.9963. Min Act: -0.0000

Data Index: 207275 (The Pile)

Max Activating Token Index: 186