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

Dataset: The Pile

Neuron 2732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1290193 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.6849. Min Act: -0.0000

Data Index: 635838 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1747717 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1338856 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1718959 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.4107. Min Act: -0.0000

Data Index: 356019 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.3536. Min Act: -0.0000

Data Index: 839600 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.3499. Min Act: -0.0000

Data Index: 384580 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.3208. Min Act: -0.0000

Data Index: 68949 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1283543 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1206225 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.3116. Min Act: -0.0000

Data Index: 695311 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.2914. Min Act: -0.0000

Data Index: 406637 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.3148. Min Act: -0.0000

Data Index: 221812 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1284916 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1630365 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.2787. Min Act: -0.0000

Data Index: 949309 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.2947. Min Act: -0.0000

Data Index: 664079 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.2685. Min Act: -0.0000

Data Index: 399192 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 1.6105. Min Range: -1.6105

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1218278 (The Pile)

Max Activating Token Index: 272