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

Dataset: The Pile

Neuron 2177 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: 0.7485. Min Range: -0.7485

Max Act: 0.7262. Min Act: -0.0000

Data Index: 113453 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.7485. Min Act: -0.0000

Data Index: 524140 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1285941 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6935. Min Act: -0.0000

Data Index: 135318 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6522. Min Act: -0.0000

Data Index: 312293 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1365457 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6516. Min Act: -0.0000

Data Index: 996580 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6680. Min Act: -0.0000

Data Index: 793533 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1598088 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1131197 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6774. Min Act: -0.0000

Data Index: 619821 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1958119 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1513071 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6816. Min Act: -0.0000

Data Index: 785650 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6379. Min Act: -0.0000

Data Index: 971645 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1256966 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6271. Min Act: -0.0000

Data Index: 197182 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1958407 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.5622. Min Act: -0.0000

Data Index: 357020 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.5693. Min Act: -0.0000

Data Index: 313134 (The Pile)

Max Activating Token Index: 22