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

Dataset: The Pile

Neuron 4705 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: 0.3821. Min Range: -0.3821

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1916722 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1118810 (The Pile)

Max Activating Token Index: 891

Text #2

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1449111 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1950252 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1704195 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1934608 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1543454 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1144451 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1076009 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1022603 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1931702 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1825983 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1627853 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2836. Min Act: -0.0000

Data Index: 550272 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3095. Min Act: -0.0000

Data Index: 990819 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1175326 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2783. Min Act: -0.0000

Data Index: 442988 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1547392 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2843. Min Act: -0.0000

Data Index: 533790 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1104197 (The Pile)

Max Activating Token Index: 975