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

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

Neuron 2444 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0003

Data Index: 1223288 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1224. Min Act: -0.0003

Data Index: 1066705 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1219. Min Act: -0.0003

Data Index: 812210 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1196. Min Act: -0.0003

Data Index: 571074 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1191. Min Act: -0.0003

Data Index: 656940 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1131. Min Act: -0.0003

Data Index: 266020 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1087. Min Act: -0.0003

Data Index: 1331700 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1094. Min Act: -0.0003

Data Index: 661232 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1100. Min Act: -0.0003

Data Index: 576992 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1052. Min Act: -0.0003

Data Index: 1088048 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1052. Min Act: -0.0003

Data Index: 472420 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1103. Min Act: -0.0003

Data Index: 468876 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1331385 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1105. Min Act: -0.0003

Data Index: 1102280 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1547555 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1052. Min Act: -0.0003

Data Index: 854184 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0963. Min Act: -0.0003

Data Index: 1220493 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1034. Min Act: -0.0003

Data Index: 225485 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1030. Min Act: -0.0003

Data Index: 1087016 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1028. Min Act: -0.0003

Data Index: 102510 (C4 (Web Text))

Max Activating Token Index: 408