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

Dataset: The Pile

Neuron 2123 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: 0.5519. Min Range: -0.5519

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1885038 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5519. Min Act: -0.0000

Data Index: 987208 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1551083 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1535090 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4093. Min Act: -0.0000

Data Index: 110682 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1043189 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3852. Min Act: -0.0000

Data Index: 80632 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4445. Min Act: -0.0000

Data Index: 65300 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1703606 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4520. Min Act: -0.0000

Data Index: 754463 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1725573 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1511156 (The Pile)

Max Activating Token Index: 840

Text #12

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1216588 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4255. Min Act: -0.0000

Data Index: 689408 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1710152 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4051. Min Act: -0.0000

Data Index: 751313 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4131. Min Act: -0.0000

Data Index: 134026 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1064557 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3609. Min Act: -0.0000

Data Index: 18312 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4139. Min Act: -0.0000

Data Index: 271371 (The Pile)

Max Activating Token Index: 755