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

Dataset: The Pile

Neuron 2870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5168. Min Range: -3.5168

Max Act: 3.4081. Min Act: -0.0000

Data Index: 104258 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 3.5168. Min Range: -3.5168

Max Act: 3.5168. Min Act: -0.0000

Data Index: 1733834 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 3.5168. Min Range: -3.5168

Max Act: 3.0722. Min Act: -0.0000

Data Index: 374771 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 3.5168. Min Range: -3.5168

Max Act: 3.0024. Min Act: -0.0000

Data Index: 1590959 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.9445. Min Act: -0.0000

Data Index: 1065398 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4057. Min Act: -0.0000

Data Index: 133219 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.6183. Min Act: -0.0000

Data Index: 303875 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.3296. Min Act: -0.0000

Data Index: 1993089 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4597. Min Act: -0.0000

Data Index: 459162 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1867314 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.1102. Min Act: -0.0000

Data Index: 302993 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.6036. Min Act: -0.0000

Data Index: 414470 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1222615 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.0870. Min Act: -0.0000

Data Index: 1721409 (The Pile)

Max Activating Token Index: 516

Text #14

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.0690. Min Act: -0.0000

Data Index: 1307689 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 3.5168. Min Range: -3.5168

Max Act: 1.9841. Min Act: -0.0000

Data Index: 1133347 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.3412. Min Act: -0.0000

Data Index: 1267546 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.2390. Min Act: -0.0000

Data Index: 1204456 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 3.5168. Min Range: -3.5168

Max Act: 1.9116. Min Act: -0.0000

Data Index: 1176873 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.1018. Min Act: -0.0000

Data Index: 169696 (The Pile)

Max Activating Token Index: 805