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

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

Neuron 320 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: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 54626 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 621826 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 778043 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1309223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 742923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1187553 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 48120 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0004

Data Index: 1036591 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0004

Data Index: 888921 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1222680 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0004

Data Index: 1127173 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 84907 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1610638 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 659331 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0004

Data Index: 1294815 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 576715 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1271268 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0004

Data Index: 1332886 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1102900 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0004

Data Index: 98129 (C4 (Web Text))

Max Activating Token Index: 310