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

Dataset: The Pile

Neuron 1583 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: 1.1107. Min Range: -1.1107

Max Act: 1.1006. Min Act: -0.0000

Data Index: 453874 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1608514 (The Pile)

Max Activating Token Index: 386

Text #2

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1760791 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1309198 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0054. Min Act: -0.0000

Data Index: 701782 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9536. Min Act: 0.0000

Data Index: 209726 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1094886 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9023. Min Act: -0.0000

Data Index: 469325 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8201. Min Act: -0.0000

Data Index: 530069 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8087. Min Act: -0.0000

Data Index: 331811 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7664. Min Act: -0.0000

Data Index: 283812 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7758. Min Act: -0.0000

Data Index: 594622 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8149. Min Act: -0.0000

Data Index: 512229 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8484. Min Act: -0.0000

Data Index: 363110 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7184. Min Act: 0.0000

Data Index: 285381 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7652. Min Act: -0.0000

Data Index: 254817 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1239169 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8048. Min Act: -0.0000

Data Index: 329165 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1596725 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1513643 (The Pile)

Max Activating Token Index: 591