Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2233 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1124. Min Act: -0.0003

Data Index: 795752 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0003

Data Index: 991759 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1140. Min Act: -0.0003

Data Index: 1236086 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1046. Min Act: -0.0003

Data Index: 746796 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1076. Min Act: -0.0003

Data Index: 264096 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1057. Min Act: -0.0003

Data Index: 575672 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1054. Min Act: -0.0003

Data Index: 714208 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1044. Min Act: -0.0003

Data Index: 1206665 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0899. Min Act: -0.0003

Data Index: 922899 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1006. Min Act: -0.0003

Data Index: 1284817 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0965. Min Act: -0.0003

Data Index: 590398 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1028. Min Act: -0.0003

Data Index: 1358269 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0955. Min Act: -0.0003

Data Index: 488686 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0974. Min Act: -0.0003

Data Index: 530013 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0972. Min Act: -0.0003

Data Index: 202349 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1002. Min Act: -0.0003

Data Index: 990220 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0963. Min Act: -0.0003

Data Index: 993926 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0996. Min Act: -0.0003

Data Index: 588040 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0922. Min Act: -0.0003

Data Index: 560770 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0941. Min Act: -0.0003

Data Index: 832367 (C4 (Web Text))

Max Activating Token Index: 462