Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 54 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1394. Min Act: -0.0002

Data Index: 117531 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1095. Min Act: -0.0002

Data Index: 494852 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1130396 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1093. Min Act: -0.0002

Data Index: 404850 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1037. Min Act: -0.0002

Data Index: 656134 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1015. Min Act: -0.0002

Data Index: 704767 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1028. Min Act: -0.0002

Data Index: 138156 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1232602 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1356985 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0974. Min Act: -0.0002

Data Index: 804174 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1015. Min Act: -0.0002

Data Index: 238921 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0976. Min Act: -0.0002

Data Index: 892183 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0960. Min Act: -0.0002

Data Index: 631073 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0981. Min Act: -0.0002

Data Index: 614460 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0963. Min Act: -0.0002

Data Index: 472750 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0918. Min Act: -0.0002

Data Index: 958375 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0927. Min Act: -0.0002

Data Index: 679859 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0947. Min Act: -0.0002

Data Index: 858643 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0926. Min Act: -0.0002

Data Index: 744129 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1104041 (C4 (Web Text))

Max Activating Token Index: 466