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

Dataset: The Pile

Neuron 3971 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: 3.4073. Min Range: -3.4073

Max Act: 3.4073. Min Act: -0.0000

Data Index: 1491751 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.3314. Min Act: -0.0000

Data Index: 342074 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.0939. Min Act: -0.0000

Data Index: 734927 (The Pile)

Max Activating Token Index: 881

Text #3

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.1323. Min Act: -0.0000

Data Index: 256582 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.9100. Min Act: -0.0000

Data Index: 244700 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7870. Min Act: -0.0000

Data Index: 889863 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.8474. Min Act: -0.0000

Data Index: 1421476 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.6974. Min Act: -0.0000

Data Index: 584834 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7760. Min Act: -0.0000

Data Index: 1369935 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7879. Min Act: -0.0000

Data Index: 1078914 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.4987. Min Act: -0.0000

Data Index: 1382764 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7669. Min Act: -0.0000

Data Index: 19181 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7518. Min Act: -0.0000

Data Index: 1783328 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7261. Min Act: -0.0000

Data Index: 934867 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7093. Min Act: -0.0000

Data Index: 1990823 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7096. Min Act: -0.0000

Data Index: 418519 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.7254. Min Act: -0.0000

Data Index: 1150340 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.8238. Min Act: -0.0000

Data Index: 497108 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.6919. Min Act: -0.0000

Data Index: 826962 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 3.4073. Min Range: -3.4073

Max Act: 2.6445. Min Act: -0.0001

Data Index: 1699032 (The Pile)

Max Activating Token Index: 568