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

Dataset: The Pile

Neuron 174 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: 0.4827. Min Range: -0.4827

Max Act: 0.4656. Min Act: -0.0000

Data Index: 552944 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1379056 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4500. Min Act: -0.0000

Data Index: 265105 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4827. Min Act: -0.0000

Data Index: 882727 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1949524 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4419. Min Act: -0.0000

Data Index: 147413 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4210. Min Act: -0.0000

Data Index: 947093 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1108463 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4075. Min Act: -0.0000

Data Index: 814220 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.4368. Min Act: -0.0000

Data Index: 212370 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1959906 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3681. Min Act: -0.0000

Data Index: 107678 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1342735 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1464891 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1897216 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1136725 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3679. Min Act: -0.0000

Data Index: 295796 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1202131 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3781. Min Act: -0.0000

Data Index: 667831 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 0.4827. Min Range: -0.4827

Max Act: 0.3370. Min Act: -0.0000

Data Index: 363244 (The Pile)

Max Activating Token Index: 652