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

Dataset: The Pile

Neuron 3756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0101. Min Range: -1.0101

Max Act: 1.0101. Min Act: -0.0000

Data Index: 273924 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.9547. Min Act: -0.0000

Data Index: 302764 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8305. Min Act: -0.0000

Data Index: 914697 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.8135. Min Act: -0.0000

Data Index: 547631 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1831343 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7924. Min Act: -0.0000

Data Index: 118361 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1356623 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1365070 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1605542 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1863046 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1975088 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1327729 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7464. Min Act: -0.0000

Data Index: 758713 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7373. Min Act: -0.0000

Data Index: 505704 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.6962. Min Act: -0.0000

Data Index: 973980 (The Pile)

Max Activating Token Index: 185

Text #15

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7044. Min Act: -0.0000

Data Index: 286172 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1006003 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.6958. Min Act: -0.0000

Data Index: 459226 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.6714. Min Act: -0.0000

Data Index: 935539 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 1.0101. Min Range: -1.0101

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1506498 (The Pile)

Max Activating Token Index: 920