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

Dataset: The Pile

Neuron 2136 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: 1.1853. Min Range: -1.1853

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1304544 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.1438. Min Act: -0.0000

Data Index: 1448177 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0037. Min Act: -0.0000

Data Index: 528565 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0580. Min Act: -0.0000

Data Index: 107108 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1264242 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9454. Min Act: -0.0000

Data Index: 308811 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1726172 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0448. Min Act: -0.0000

Data Index: 935913 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8112. Min Act: -0.0000

Data Index: 20005 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1400451 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1248170 (The Pile)

Max Activating Token Index: 801

Text #11

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6484. Min Act: -0.0000

Data Index: 887532 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1876930 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1818251 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.7019. Min Act: -0.0000

Data Index: 471308 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6438. Min Act: -0.0000

Data Index: 738746 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1638985 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6817. Min Act: -0.0000

Data Index: 973144 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1079043 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.6602. Min Act: -0.0000

Data Index: 953173 (The Pile)

Max Activating Token Index: 956