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

Dataset: The Pile

Neuron 592 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6847. Min Act: -0.0000

Data Index: 865428 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1298230 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1293500 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5351. Min Act: -0.0000

Data Index: 646563 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5258. Min Act: -0.0000

Data Index: 937122 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5254. Min Act: -0.0000

Data Index: 912342 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1069649 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4864. Min Act: -0.0000

Data Index: 379465 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4851. Min Act: -0.0000

Data Index: 594065 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1233808 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1125966 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1423946 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4490. Min Act: -0.0000

Data Index: 939013 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4577. Min Act: -0.0000

Data Index: 956442 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1725166 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1004253 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1258111 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4406. Min Act: 0.0000

Data Index: 285692 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1560264 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1518471 (The Pile)

Max Activating Token Index: 223