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

Dataset: The Pile

Neuron 3506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0311. Min Range: -3.0311

Max Act: 3.0311. Min Act: -0.0000

Data Index: 15239 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.4703. Min Act: -0.0000

Data Index: 1716348 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.5929. Min Act: -0.0000

Data Index: 1120728 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.3661. Min Act: -0.0000

Data Index: 661767 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.3927. Min Act: -0.0000

Data Index: 1121024 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.2875. Min Act: -0.0000

Data Index: 1285997 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.0371. Min Act: -0.0000

Data Index: 80906 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.9089. Min Act: -0.0000

Data Index: 1453707 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.0104. Min Act: -0.0000

Data Index: 1264398 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.0105. Min Act: -0.0000

Data Index: 279009 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.0029. Min Act: -0.0000

Data Index: 1953399 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.8975. Min Act: -0.0000

Data Index: 829064 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.9801. Min Act: -0.0000

Data Index: 1736145 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.9862. Min Act: -0.0000

Data Index: 1586320 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.9392. Min Act: -0.0000

Data Index: 1292466 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 3.0311. Min Range: -3.0311

Max Act: 2.0177. Min Act: -0.0000

Data Index: 1029359 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.7833. Min Act: -0.0000

Data Index: 1130480 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.8878. Min Act: -0.0000

Data Index: 712287 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.8549. Min Act: -0.0000

Data Index: 791287 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 3.0311. Min Range: -3.0311

Max Act: 1.8519. Min Act: -0.0000

Data Index: 1453248 (The Pile)

Max Activating Token Index: 31