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

Dataset: The Pile

Neuron 4865 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1795268 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1377025 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7339. Min Act: -0.0000

Data Index: 860071 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8830. Min Act: -0.0000

Data Index: 182586 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8814. Min Act: -0.0000

Data Index: 184053 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1550650 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8877. Min Act: -0.0000

Data Index: 551360 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1294785 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1913652 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7822. Min Act: -0.0000

Data Index: 21493 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8657. Min Act: -0.0000

Data Index: 339493 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7273. Min Act: -0.0000

Data Index: 996894 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8341. Min Act: -0.0000

Data Index: 170379 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1613633 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7613. Min Act: -0.0000

Data Index: 274644 (The Pile)

Max Activating Token Index: 96

Text #15

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8105. Min Act: -0.0000

Data Index: 699089 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1183650 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6578. Min Act: -0.0000

Data Index: 434882 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1528807 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1030582 (The Pile)

Max Activating Token Index: 178