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

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

Neuron 651 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4101. Min Range: -2.4101

Max Act: 2.4101. Min Act: -0.0000

Data Index: 777596 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.5139. Min Act: -0.0000

Data Index: 67326 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.4376. Min Act: -0.0000

Data Index: 821877 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.4680. Min Act: -0.0000

Data Index: 775705 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.3779. Min Act: -0.0000

Data Index: 12984 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.3280. Min Act: -0.0000

Data Index: 885045 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.2400. Min Act: -0.0000

Data Index: 34218 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.1524. Min Act: -0.0000

Data Index: 632437 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1072857 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.0669. Min Act: -0.0000

Data Index: 582436 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.0566. Min Act: -0.0000

Data Index: 437948 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.0547. Min Act: -0.0000

Data Index: 563868 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 2.4101. Min Range: -2.4101

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1010425 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 2.4101. Min Range: -2.4101

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1301982 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 2.4101. Min Range: -2.4101

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1108130 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 2.4101. Min Range: -2.4101

Max Act: 0.9761. Min Act: -0.0000

Data Index: 665912 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 2.4101. Min Range: -2.4101

Max Act: 0.9063. Min Act: -0.0000

Data Index: 524282 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 2.4101. Min Range: -2.4101

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1270046 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 2.4101. Min Range: -2.4101

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1230077 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.4101. Min Range: -2.4101

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1291974 (C4 (Web Text))

Max Activating Token Index: 861