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

Dataset: The Pile

Neuron 4787 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.2943. Min Act: -0.0000

Data Index: 711089 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1791. Min Act: -0.0000

Data Index: 1462345 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1338942 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1377405 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1436. Min Act: -0.0000

Data Index: 203709 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0120. Min Act: -0.0000

Data Index: 980165 (The Pile)

Max Activating Token Index: 491

Text #6

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0750. Min Act: -0.0000

Data Index: 153318 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9875. Min Act: -0.0000

Data Index: 926753 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9169. Min Act: -0.0000

Data Index: 398255 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0116. Min Act: -0.0000

Data Index: 35289 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1500503 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1475180 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1528377 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9345. Min Act: -0.0001

Data Index: 1094981 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1645079 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1329271 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1828224 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9118. Min Act: -0.0001

Data Index: 1732595 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1689327 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8670. Min Act: -0.0000

Data Index: 758678 (The Pile)

Max Activating Token Index: 223