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

Dataset: The Pile

Neuron 3409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1212447 (The Pile)

Max Activating Token Index: 889

Text #1

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1781024 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5367. Min Act: -0.0000

Data Index: 325186 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1602946 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5026. Min Act: -0.0000

Data Index: 964550 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1218074 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1004824 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1743100 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1971589 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4565. Min Act: -0.0000

Data Index: 250172 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1085183 (The Pile)

Max Activating Token Index: 957

Text #11

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4200. Min Act: -0.0000

Data Index: 174086 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4464. Min Act: -0.0000

Data Index: 718172 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4169. Min Act: -0.0001

Data Index: 529674 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4007. Min Act: -0.0000

Data Index: 846796 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3954. Min Act: -0.0000

Data Index: 236620 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4173. Min Act: -0.0000

Data Index: 850189 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1690980 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4086. Min Act: -0.0000

Data Index: 952867 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1916883 (The Pile)

Max Activating Token Index: 169