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

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

Neuron 32 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: 0.1439. Min Range: -0.1439

Max Act: 0.1415. Min Act: -0.0001

Data Index: 910341 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1051326 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1439. Min Act: -0.0001

Data Index: 634195 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1335886 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1153240 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1351821 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1115258 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1167. Min Act: -0.0001

Data Index: 996169 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1197. Min Act: -0.0001

Data Index: 70760 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1144. Min Act: -0.0001

Data Index: 138465 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1019. Min Act: -0.0001

Data Index: 681306 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1175. Min Act: -0.0001

Data Index: 630573 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1127. Min Act: -0.0001

Data Index: 920877 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1145. Min Act: -0.0001

Data Index: 848045 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1071. Min Act: -0.0001

Data Index: 698955 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1103. Min Act: -0.0001

Data Index: 539007 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0941. Min Act: -0.0001

Data Index: 479354 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1089. Min Act: -0.0001

Data Index: 859080 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1107. Min Act: -0.0001

Data Index: 514962 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1211135 (C4 (Web Text))

Max Activating Token Index: 720