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

Dataset: The Pile

Neuron 3909 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4827. Min Range: -3.4827

Max Act: 3.4827. Min Act: -0.0000

Data Index: 1084304 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 3.4827. Min Range: -3.4827

Max Act: 3.0887. Min Act: -0.0000

Data Index: 1449790 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.9865. Min Act: -0.0000

Data Index: 502398 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.9181. Min Act: -0.0000

Data Index: 1431212 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.7101. Min Act: -0.0000

Data Index: 200483 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 3.4827. Min Range: -3.4827

Max Act: 3.0959. Min Act: -0.0000

Data Index: 1045878 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 3.4827. Min Range: -3.4827

Max Act: 3.0229. Min Act: -0.0000

Data Index: 1407555 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.7743. Min Act: -0.0000

Data Index: 282447 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.6871. Min Act: -0.0000

Data Index: 558949 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.5166. Min Act: -0.0000

Data Index: 1328425 (The Pile)

Max Activating Token Index: 82

Text #10

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.0118. Min Act: -0.0000

Data Index: 268421 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.5619. Min Act: -0.0000

Data Index: 733163 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.0271. Min Act: -0.0000

Data Index: 649854 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.3868. Min Act: -0.0000

Data Index: 805773 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 3.4827. Min Range: -3.4827

Max Act: 1.9289. Min Act: -0.0000

Data Index: 1951223 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.0965. Min Act: -0.0000

Data Index: 545521 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.1962. Min Act: -0.0000

Data Index: 1171496 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.1635. Min Act: -0.0000

Data Index: 750370 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 3.4827. Min Range: -3.4827

Max Act: 1.9662. Min Act: -0.0000

Data Index: 840273 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 3.4827. Min Range: -3.4827

Max Act: 2.0864. Min Act: -0.0000

Data Index: 20890 (The Pile)

Max Activating Token Index: 188