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

Dataset: The Pile

Neuron 2050 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: 0.9455. Min Range: -0.9455

Max Act: 0.9455. Min Act: -0.0000

Data Index: 4927 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1923980 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.8114. Min Act: -0.0000

Data Index: 171917 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1287942 (The Pile)

Max Activating Token Index: 600

Text #4

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7531. Min Act: 0.0000

Data Index: 1871806 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.8120. Min Act: -0.0000

Data Index: 274314 (The Pile)

Max Activating Token Index: 87

Text #6

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.8021. Min Act: -0.0000

Data Index: 709981 (The Pile)

Max Activating Token Index: 471

Text #7

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1300152 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1250082 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1165938 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1516133 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1348134 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1355049 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1999728 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6336. Min Act: -0.0000

Data Index: 738739 (The Pile)

Max Activating Token Index: 474

Text #15

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1337199 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1315294 (The Pile)

Max Activating Token Index: 727

Text #17

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6434. Min Act: -0.0000

Data Index: 262883 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7635. Min Act: 0.0000

Data Index: 302219 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7074. Min Act: -0.0000

Data Index: 197754 (The Pile)

Max Activating Token Index: 428