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

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

Neuron 3510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.5179. Min Act: -0.0001

Data Index: 1069543 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.2982. Min Act: -0.0001

Data Index: 461998 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.2084. Min Act: -0.0001

Data Index: 1184885 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.1001. Min Act: -0.0001

Data Index: 1191157 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.0232. Min Act: -0.0001

Data Index: 649756 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.0359. Min Act: -0.0001

Data Index: 927291 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.0498. Min Act: -0.0001

Data Index: 878210 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.0350. Min Act: -0.0001

Data Index: 971436 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.5179. Min Range: -1.5179

Max Act: 1.0039. Min Act: -0.0001

Data Index: 1033867 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.9036. Min Act: -0.0001

Data Index: 1019140 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.9126. Min Act: -0.0001

Data Index: 766024 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.9058. Min Act: -0.0001

Data Index: 920223 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.8981. Min Act: -0.0001

Data Index: 330039 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.8385. Min Act: -0.0001

Data Index: 173053 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.8299. Min Act: -0.0001

Data Index: 636999 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.7944. Min Act: -0.0001

Data Index: 639052 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.7946. Min Act: -0.0001

Data Index: 9381 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.7927. Min Act: -0.0001

Data Index: 559833 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.7914. Min Act: -0.0001

Data Index: 1215126 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 1.5179. Min Range: -1.5179

Max Act: 0.7959. Min Act: -0.0001

Data Index: 380291 (C4 (Web Text))

Max Activating Token Index: 843