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

Dataset: The Pile

Neuron 1626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1172589 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7539. Min Act: -0.0000

Data Index: 495565 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7595. Min Act: -0.0000

Data Index: 233950 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7612. Min Act: 0.0001

Data Index: 468388 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1757923 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7745. Min Act: -0.0000

Data Index: 141558 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1892039 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1018995 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1294610 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1014705 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7180. Min Act: -0.0000

Data Index: 515960 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7398. Min Act: 0.0000

Data Index: 694471 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1592330 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7572. Min Act: -0.0000

Data Index: 207280 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7048. Min Act: 0.0000

Data Index: 1624707 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.6705. Min Act: -0.0000

Data Index: 56804 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.7393. Min Act: -0.0000

Data Index: 168066 (The Pile)

Max Activating Token Index: 915

Text #17

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1261924 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.6640. Min Act: -0.0000

Data Index: 871140 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.6855. Min Act: -0.0000

Data Index: 881277 (The Pile)

Max Activating Token Index: 184