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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3408 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3781. Min Act: -0.0000

Data Index: 545600 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.4081. Min Act: -0.0000

Data Index: 772277 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1431727 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1586298 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3537. Min Act: -0.0000

Data Index: 546915 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3844. Min Act: -0.0000

Data Index: 625249 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3012. Min Act: -0.0000

Data Index: 883130 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3048. Min Act: -0.0000

Data Index: 651177 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3264. Min Act: -0.0000

Data Index: 606245 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3216. Min Act: -0.0000

Data Index: 802002 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3039. Min Act: -0.0000

Data Index: 15162 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1058018 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2942. Min Act: -0.0000

Data Index: 77850 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1557304 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1472625 (Python Code)

Max Activating Token Index: 557

Text #17

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1385282 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3135. Min Act: -0.0000

Data Index: 500134 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1140563 (C4 (Web Text))

Max Activating Token Index: 286