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

Dataset: The Pile

Neuron 4890 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8703. Min Act: -0.0000

Data Index: 642090 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.5360. Min Act: -0.0000

Data Index: 150757 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4735. Min Act: -0.0000

Data Index: 591451 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1878702 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4352. Min Act: -0.0000

Data Index: 159523 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4650. Min Act: -0.0000

Data Index: 101712 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4814. Min Act: -0.0000

Data Index: 796792 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1455386 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4489. Min Act: -0.0000

Data Index: 103939 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1286446 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4225. Min Act: -0.0000

Data Index: 116390 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1919106 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4516. Min Act: -0.0000

Data Index: 266627 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1992511 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4090. Min Act: -0.0000

Data Index: 46188 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4052. Min Act: -0.0000

Data Index: 900118 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.3956. Min Act: -0.0000

Data Index: 973094 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1360935 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1997422 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.4270. Min Act: -0.0000

Data Index: 372016 (The Pile)

Max Activating Token Index: 308