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

Dataset: The Pile

Neuron 2415 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8233. Min Act: -0.0000

Data Index: 389477 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1610213 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7801. Min Act: -0.0000

Data Index: 492060 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7995. Min Act: -0.0000

Data Index: 632659 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8170. Min Act: -0.0000

Data Index: 333231 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7938. Min Act: -0.0000

Data Index: 362933 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1322529 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1057804 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1545307 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1795957 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6853. Min Act: -0.0000

Data Index: 789307 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1597814 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1922570 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7226. Min Act: -0.0000

Data Index: 791335 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7042. Min Act: -0.0000

Data Index: 586116 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1284489 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7071. Min Act: -0.0000

Data Index: 745703 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7097. Min Act: -0.0000

Data Index: 641621 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1051802 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1245158 (The Pile)

Max Activating Token Index: 809