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

Dataset: The Pile

Neuron 3244 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1626840 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1244852 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1742854 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1214897 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1252682 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5511. Min Act: -0.0000

Data Index: 183968 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1679097 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1917182 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5189. Min Act: -0.0000

Data Index: 635630 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1719212 (The Pile)

Max Activating Token Index: 469

Text #10

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5219. Min Act: -0.0000

Data Index: 324133 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5203. Min Act: -0.0000

Data Index: 359943 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5151. Min Act: -0.0000

Data Index: 527122 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5494. Min Act: -0.0000

Data Index: 554882 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5164. Min Act: -0.0000

Data Index: 512998 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1191407 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5006. Min Act: -0.0000

Data Index: 106445 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1965065 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1888404 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1457236 (The Pile)

Max Activating Token Index: 503