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

Dataset: The Pile

Neuron 4073 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: 0.7206. Min Range: -0.7206

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1579401 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1163903 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6476. Min Act: -0.0000

Data Index: 197099 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1929610 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6332. Min Act: -0.0000

Data Index: 934232 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6107. Min Act: -0.0000

Data Index: 229756 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6104. Min Act: -0.0000

Data Index: 140255 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5885. Min Act: -0.0000

Data Index: 855200 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6001. Min Act: -0.0000

Data Index: 261335 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5724. Min Act: -0.0000

Data Index: 311905 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5568. Min Act: -0.0000

Data Index: 855209 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1832987 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1547508 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5257. Min Act: -0.0000

Data Index: 688913 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1744779 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5133. Min Act: -0.0000

Data Index: 165502 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1842592 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4925. Min Act: -0.0000

Data Index: 504152 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4730. Min Act: -0.0000

Data Index: 911261 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4827. Min Act: -0.0000

Data Index: 937456 (The Pile)

Max Activating Token Index: 470