Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2371 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1647730 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.4325. Min Act: -0.0000

Data Index: 655318 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1490018 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1083879 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.3201. Min Act: -0.0000

Data Index: 289784 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2254. Min Act: -0.0000

Data Index: 897980 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2285. Min Act: -0.0000

Data Index: 783069 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1765428 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1592812 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1672965 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1338611 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2489. Min Act: -0.0000

Data Index: 193396 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2172. Min Act: -0.0000

Data Index: 885501 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2568. Min Act: -0.0000

Data Index: 454874 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2018. Min Act: -0.0000

Data Index: 45823 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1052930 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1976. Min Act: -0.0000

Data Index: 981343 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1539. Min Act: -0.0000

Data Index: 851104 (The Pile)

Max Activating Token Index: 678

Text #18

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1075874 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1572822 (The Pile)

Max Activating Token Index: 83