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

Dataset: The Pile

Neuron 2685 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: 0.5589. Min Range: -0.5589

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1290360 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4999. Min Act: -0.0000

Data Index: 930607 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1235994 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1216470 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4217. Min Act: -0.0000

Data Index: 805405 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4565. Min Act: -0.0000

Data Index: 322182 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1144576 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4346. Min Act: -0.0000

Data Index: 787837 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4238. Min Act: -0.0000

Data Index: 45109 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1720422 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3269. Min Act: -0.0000

Data Index: 271363 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3882. Min Act: -0.0000

Data Index: 818341 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3862. Min Act: -0.0000

Data Index: 364214 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3803. Min Act: -0.0000

Data Index: 917351 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1175882 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1946765 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3433. Min Act: -0.0000

Data Index: 732384 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1978867 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1244935 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1882027 (The Pile)

Max Activating Token Index: 689