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

Dataset: The Pile

Neuron 2258 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: 0.7931. Min Range: -0.7931

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1283075 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6601. Min Act: -0.0000

Data Index: 414185 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7032. Min Act: -0.0000

Data Index: 181856 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1189111 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6368. Min Act: -0.0000

Data Index: 240254 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7133. Min Act: -0.0000

Data Index: 583509 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1181492 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1511952 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6400. Min Act: -0.0000

Data Index: 768384 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1146412 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1429783 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1209480 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1085839 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5782. Min Act: -0.0000

Data Index: 577622 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5855. Min Act: -0.0000

Data Index: 761547 (The Pile)

Max Activating Token Index: 283

Text #15

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5643. Min Act: -0.0000

Data Index: 360199 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1054166 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5730. Min Act: -0.0000

Data Index: 280831 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1971908 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1782770 (The Pile)

Max Activating Token Index: 435