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

Dataset: The Pile

Neuron 2438 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: 1.5284. Min Range: -1.5284

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1542610 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1868125 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1734165 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2397. Min Act: -0.0000

Data Index: 49408 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2958. Min Act: -0.0000

Data Index: 869490 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.5284. Min Act: -0.0000

Data Index: 1181831 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.4043. Min Act: -0.0000

Data Index: 165234 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.3221. Min Act: -0.0000

Data Index: 307473 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2346. Min Act: -0.0000

Data Index: 826675 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.3071. Min Act: -0.0000

Data Index: 957777 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1197050 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.1605. Min Act: -0.0000

Data Index: 367413 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2941. Min Act: -0.0000

Data Index: 111888 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2875. Min Act: -0.0000

Data Index: 620051 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2091. Min Act: -0.0000

Data Index: 236870 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.1444. Min Act: -0.0000

Data Index: 575040 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1986658 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.0713. Min Act: -0.0000

Data Index: 343654 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2070. Min Act: -0.0000

Data Index: 149968 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 1.5284. Min Range: -1.5284

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1263845 (The Pile)

Max Activating Token Index: 466