Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.1648. Min Act: -0.0000

Data Index: 397748 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.1479. Min Act: -0.0000

Data Index: 787225 (The Pile)

Max Activating Token Index: 202

Text #2

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0344. Min Act: -0.0000

Data Index: 56462 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1606283 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1332330 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1598178 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1623778 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1158856 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1668110 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9750. Min Act: -0.0000

Data Index: 707625 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0346. Min Act: -0.0000

Data Index: 694884 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9520. Min Act: -0.0000

Data Index: 724381 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1963271 (The Pile)

Max Activating Token Index: 299

Text #13

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1101277 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8753. Min Act: -0.0000

Data Index: 927317 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1871926 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1998872 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1825952 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8887. Min Act: -0.0000

Data Index: 488850 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8872. Min Act: -0.0000

Data Index: 241025 (The Pile)

Max Activating Token Index: 285