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

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

Neuron 1412 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0001

Data Index: 694280 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1187. Min Act: -0.0001

Data Index: 373335 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1175. Min Act: -0.0001

Data Index: 609362 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1128. Min Act: -0.0001

Data Index: 886364 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1121. Min Act: -0.0001

Data Index: 238099 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1106. Min Act: -0.0001

Data Index: 384789 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1107. Min Act: -0.0001

Data Index: 194692 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1095. Min Act: -0.0001

Data Index: 795586 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1133. Min Act: -0.0001

Data Index: 32724 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1092. Min Act: -0.0001

Data Index: 11866 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1321551 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1080. Min Act: -0.0001

Data Index: 955344 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1286616 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1016. Min Act: -0.0001

Data Index: 140933 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0987. Min Act: -0.0001

Data Index: 789362 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0991. Min Act: -0.0001

Data Index: 826374 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1079. Min Act: -0.0001

Data Index: 38375 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1064601 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1028. Min Act: -0.0001

Data Index: 549624 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0957. Min Act: -0.0001

Data Index: 322886 (C4 (Web Text))

Max Activating Token Index: 490