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

Dataset: The Pile

Neuron 420 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7070. Min Act: -0.0000

Data Index: 817544 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7439. Min Act: -0.0000

Data Index: 406176 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6558. Min Act: -0.0000

Data Index: 166978 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1049197 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1833379 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1015133 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5514. Min Act: -0.0000

Data Index: 85469 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5489. Min Act: 0.0000

Data Index: 610322 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5176. Min Act: -0.0000

Data Index: 985079 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1834031 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5253. Min Act: -0.0000

Data Index: 720980 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1251382 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4886. Min Act: -0.0000

Data Index: 738137 (The Pile)

Max Activating Token Index: 933

Text #13

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5299. Min Act: -0.0000

Data Index: 48811 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5114. Min Act: -0.0000

Data Index: 676427 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1982010 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5040. Min Act: -0.0000

Data Index: 753849 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1414104 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4343. Min Act: 0.0000

Data Index: 708215 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4829. Min Act: -0.0000

Data Index: 969799 (The Pile)

Max Activating Token Index: 140