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

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

Neuron 567 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: 0.1125. Min Range: -0.1125

Max Act: 0.1078. Min Act: -0.0002

Data Index: 911199 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1125. Min Act: -0.0002

Data Index: 842448 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1058. Min Act: -0.0002

Data Index: 141644 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1107. Min Act: -0.0002

Data Index: 913900 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0984. Min Act: -0.0002

Data Index: 386593 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1108. Min Act: -0.0002

Data Index: 639746 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1024. Min Act: -0.0002

Data Index: 509677 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1036. Min Act: -0.0002

Data Index: 948421 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0970. Min Act: -0.0002

Data Index: 552102 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0950. Min Act: -0.0002

Data Index: 29044 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0961. Min Act: -0.0002

Data Index: 969380 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1323674 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1101923 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0990. Min Act: -0.0002

Data Index: 211051 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0958. Min Act: -0.0002

Data Index: 562656 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0916. Min Act: -0.0002

Data Index: 739620 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0968. Min Act: -0.0002

Data Index: 886546 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1331291 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0810. Min Act: -0.0002

Data Index: 451412 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1197619 (C4 (Web Text))

Max Activating Token Index: 697