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

Dataset: The Pile

Neuron 3535 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: 0.9947. Min Range: -0.9947

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1237840 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8644. Min Act: -0.0000

Data Index: 948771 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8940. Min Act: -0.0000

Data Index: 321017 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8747. Min Act: -0.0000

Data Index: 325081 (The Pile)

Max Activating Token Index: 25

Text #4

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9189. Min Act: -0.0000

Data Index: 384699 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8012. Min Act: -0.0000

Data Index: 435246 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1050651 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1397805 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8101. Min Act: -0.0000

Data Index: 109809 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7619. Min Act: -0.0000

Data Index: 503579 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1661627 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7063. Min Act: -0.0000

Data Index: 978248 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1294337 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1484861 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1267418 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1573807 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7437. Min Act: -0.0000

Data Index: 210974 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7693. Min Act: -0.0000

Data Index: 906979 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1380081 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7311. Min Act: -0.0000

Data Index: 994604 (The Pile)

Max Activating Token Index: 282