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

Dataset: The Pile

Neuron 1036 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5891. Min Act: -0.0000

Data Index: 208324 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4875. Min Act: -0.0000

Data Index: 132275 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1975380 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1539858 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5612. Min Act: -0.0000

Data Index: 950327 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4932. Min Act: -0.0000

Data Index: 673906 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5503. Min Act: -0.0000

Data Index: 51192 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1587341 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1095850 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1402183 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5046. Min Act: -0.0000

Data Index: 20608 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1283069 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1929114 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1571625 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4723. Min Act: -0.0000

Data Index: 526554 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1114552 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4488. Min Act: -0.0000

Data Index: 317943 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4543. Min Act: -0.0000

Data Index: 78850 (The Pile)

Max Activating Token Index: 765

Text #18

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4445. Min Act: -0.0000

Data Index: 289968 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4057. Min Act: -0.0000

Data Index: 502012 (The Pile)

Max Activating Token Index: 199