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

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

Neuron 2724 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1019862 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1118517 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1232. Min Act: -0.0001

Data Index: 901000 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1313423 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1118. Min Act: -0.0001

Data Index: 97038 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1150109 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1333897 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1095. Min Act: -0.0001

Data Index: 601844 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1037619 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0986. Min Act: -0.0001

Data Index: 833869 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1299200 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1308689 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1055182 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0893. Min Act: -0.0001

Data Index: 110157 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0858. Min Act: -0.0001

Data Index: 303820 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0853. Min Act: -0.0001

Data Index: 299940 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0865. Min Act: -0.0001

Data Index: 963108 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0862. Min Act: -0.0001

Data Index: 302938 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0783. Min Act: -0.0001

Data Index: 801220 (C4 (Web Text))

Max Activating Token Index: 21