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

Dataset: The Pile

Neuron 4941 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: 1.0206. Min Range: -1.0206

Max Act: 1.0206. Min Act: 0.0000

Data Index: 1043607 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9872. Min Act: -0.0000

Data Index: 678455 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1177163 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8874. Min Act: -0.0000

Data Index: 876606 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9088. Min Act: -0.0000

Data Index: 883103 (The Pile)

Max Activating Token Index: 156

Text #5

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9090. Min Act: 0.0000

Data Index: 1117998 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8716. Min Act: -0.0000

Data Index: 919892 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8684. Min Act: -0.0000

Data Index: 583823 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1342014 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1167925 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8388. Min Act: -0.0000

Data Index: 687758 (The Pile)

Max Activating Token Index: 648

Text #11

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1019226 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8842. Min Act: -0.0000

Data Index: 904135 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8918. Min Act: -0.0000

Data Index: 710077 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9091. Min Act: -0.0000

Data Index: 633181 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1287038 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8318. Min Act: 0.0000

Data Index: 162951 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1812444 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9076. Min Act: -0.0000

Data Index: 937870 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8521. Min Act: 0.0000

Data Index: 1820658 (The Pile)

Max Activating Token Index: 803