Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1326 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.5902. Min Act: -0.0000

Data Index: 1276978 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.9052. Min Act: -0.0000

Data Index: 636813 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.7337. Min Act: -0.0000

Data Index: 207436 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.4049. Min Act: -0.0000

Data Index: 36643 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.3961. Min Act: -0.0000

Data Index: 430514 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.2911. Min Act: -0.0000

Data Index: 814980 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.2625. Min Act: -0.0000

Data Index: 67174 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.0116. Min Act: -0.0000

Data Index: 1267982 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 3.9052. Min Range: -3.9052

Max Act: 3.0934. Min Act: -0.0000

Data Index: 232545 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.9486. Min Act: -0.0000

Data Index: 440965 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.8996. Min Act: -0.0000

Data Index: 1003739 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.8404. Min Act: -0.0000

Data Index: 963886 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.8138. Min Act: -0.0000

Data Index: 148207 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.6630. Min Act: -0.0000

Data Index: 292863 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.6485. Min Act: -0.0000

Data Index: 650860 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.7418. Min Act: -0.0000

Data Index: 398948 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.5876. Min Act: -0.0000

Data Index: 560510 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.7014. Min Act: -0.0000

Data Index: 174574 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.6850. Min Act: -0.0000

Data Index: 827845 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 3.9052. Min Range: -3.9052

Max Act: 2.6763. Min Act: -0.0000

Data Index: 342770 (C4 (Web Text))

Max Activating Token Index: 365