Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 665 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3610. Min Act: -0.0000

Data Index: 79787 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3630. Min Act: -0.0001

Data Index: 1153963 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3317. Min Act: -0.0001

Data Index: 1100870 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3434. Min Act: -0.0001

Data Index: 768258 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3067. Min Act: -0.0001

Data Index: 935278 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1054861 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3244. Min Act: -0.0000

Data Index: 525827 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3219. Min Act: -0.0001

Data Index: 893364 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3520. Min Act: -0.0000

Data Index: 340300 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3166. Min Act: -0.0001

Data Index: 335489 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3460. Min Act: -0.0001

Data Index: 917613 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3130. Min Act: -0.0001

Data Index: 1240561 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3115. Min Act: -0.0001

Data Index: 392297 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3207. Min Act: -0.0001

Data Index: 870074 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1130922 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3070. Min Act: -0.0000

Data Index: 741256 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.2908. Min Act: -0.0001

Data Index: 545739 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1272213 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.2910. Min Act: -0.0001

Data Index: 778282 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.3630. Min Range: -0.3630

Max Act: 0.3090. Min Act: -0.0001

Data Index: 522566 (C4 (Web Text))

Max Activating Token Index: 896