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

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

Neuron 2537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.4057. Min Act: -0.0001

Data Index: 648920 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3656. Min Act: -0.0001

Data Index: 267359 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3439. Min Act: -0.0001

Data Index: 387954 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3498. Min Act: -0.0001

Data Index: 526612 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3354. Min Act: -0.0001

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3107. Min Act: -0.0001

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3072. Min Act: -0.0001

Data Index: 1153809 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1021129 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3140. Min Act: -0.0001

Data Index: 766750 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2916. Min Act: -0.0001

Data Index: 88859 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2956. Min Act: -0.0001

Data Index: 496196 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2876. Min Act: -0.0001

Data Index: 563510 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3012. Min Act: -0.0001

Data Index: 709634 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.3006. Min Act: -0.0001

Data Index: 514506 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1250758 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2965. Min Act: -0.0001

Data Index: 34929 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2845. Min Act: -0.0001

Data Index: 919738 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2781. Min Act: -0.0001

Data Index: 479009 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2824. Min Act: -0.0001

Data Index: 80673 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.4057. Min Range: -0.4057

Max Act: 0.2752. Min Act: -0.0001

Data Index: 1304441 (C4 (Web Text))

Max Activating Token Index: 649