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

Dataset: The Pile

Neuron 284 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0831. Min Range: -1.0831

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1347751 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9443. Min Act: -0.0000

Data Index: 796375 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9690. Min Act: -0.0000

Data Index: 499726 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 1.0831. Min Range: -1.0831

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1140483 (The Pile)

Max Activating Token Index: 84

Text #4

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1782040 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 1.0831. Min Range: -1.0831

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1292129 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1925193 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1608562 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9632. Min Act: -0.0000

Data Index: 755371 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9391. Min Act: -0.0000

Data Index: 362109 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1212570 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9341. Min Act: -0.0000

Data Index: 240609 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1181428 (The Pile)

Max Activating Token Index: 666

Text #13

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9143. Min Act: -0.0000

Data Index: 776769 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.8947. Min Act: -0.0000

Data Index: 859107 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1084292 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1090223 (The Pile)

Max Activating Token Index: 623

Text #17

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9001. Min Act: -0.0000

Data Index: 207716 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.8601. Min Act: -0.0000

Data Index: 333664 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 1.0831. Min Range: -1.0831

Max Act: 0.9496. Min Act: -0.0000

Data Index: 218667 (The Pile)

Max Activating Token Index: 990