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

Dataset: The Pile

Neuron 1140 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: 0.8563. Min Range: -0.8563

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1137658 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1104365 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8542. Min Act: -0.0000

Data Index: 124065 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1541860 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8488. Min Act: -0.0000

Data Index: 273022 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1995093 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1306034 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7710. Min Act: -0.0000

Data Index: 643032 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7406. Min Act: -0.0000

Data Index: 583007 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1176727 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1630 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7642. Min Act: -0.0000

Data Index: 658147 (The Pile)

Max Activating Token Index: 856

Text #12

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1560681 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7267. Min Act: -0.0000

Data Index: 52292 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7432. Min Act: -0.0000

Data Index: 793777 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7368. Min Act: -0.0000

Data Index: 816354 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7290. Min Act: -0.0000

Data Index: 166681 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7514. Min Act: -0.0000

Data Index: 254057 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6774. Min Act: -0.0000

Data Index: 315213 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7164. Min Act: -0.0000

Data Index: 935320 (The Pile)

Max Activating Token Index: 577