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

Dataset: The Pile

Neuron 1938 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: 5.4078. Min Range: -5.4078

Max Act: 5.4078. Min Act: -0.0000

Data Index: 1268560 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 5.4078. Min Range: -5.4078

Max Act: 5.0566. Min Act: -0.0000

Data Index: 1093785 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.3339. Min Act: -0.0000

Data Index: 1248169 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.5452. Min Act: -0.0000

Data Index: 1259014 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.2402. Min Act: -0.0000

Data Index: 371243 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.1848. Min Act: -0.0000

Data Index: 690704 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.3064. Min Act: -0.0000

Data Index: 1630262 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.3081. Min Act: -0.0000

Data Index: 1995434 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.2834. Min Act: -0.0000

Data Index: 200464 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 5.4078. Min Range: -5.4078

Max Act: 3.9241. Min Act: -0.0000

Data Index: 1439315 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.0496. Min Act: -0.0000

Data Index: 1880727 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.1558. Min Act: -0.0000

Data Index: 1273201 (The Pile)

Max Activating Token Index: 803

Text #12

Max Range: 5.4078. Min Range: -5.4078

Max Act: 3.9317. Min Act: -0.0000

Data Index: 1604944 (The Pile)

Max Activating Token Index: 853

Text #13

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.0067. Min Act: -0.0000

Data Index: 931578 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.6540. Min Act: -0.0000

Data Index: 1355590 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 5.4078. Min Range: -5.4078

Max Act: 4.0665. Min Act: -0.0000

Data Index: 1519090 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 5.4078. Min Range: -5.4078

Max Act: 3.6373. Min Act: -0.0000

Data Index: 1223511 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 5.4078. Min Range: -5.4078

Max Act: 3.7780. Min Act: -0.0000

Data Index: 1572427 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 5.4078. Min Range: -5.4078

Max Act: 3.7080. Min Act: -0.0000

Data Index: 651185 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 5.4078. Min Range: -5.4078

Max Act: 3.6626. Min Act: -0.0000

Data Index: 1783366 (The Pile)

Max Activating Token Index: 464