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

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

Neuron 976 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0062. Min Act: -0.0003

Data Index: 965339 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0061. Min Act: -0.0004

Data Index: 291141 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1267182 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0059. Min Act: -0.0004

Data Index: 932965 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0058. Min Act: -0.0004

Data Index: 1267074 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0058. Min Act: -0.0003

Data Index: 663680 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0057. Min Act: -0.0004

Data Index: 1217892 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1325985 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0004

Data Index: 735112 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1123236 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0004

Data Index: 1036891 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0003

Data Index: 588665 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0004

Data Index: 648888 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1616933 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1192551 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1655793 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0052. Min Act: -0.0004

Data Index: 694033 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0052. Min Act: -0.0003

Data Index: 116564 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1443173 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0052. Min Act: -0.0003

Data Index: 841970 (C4 (Web Text))

Max Activating Token Index: 807