Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4960 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.1266. Min Act: -0.0001

Data Index: 1232012 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0402. Min Act: -0.0001

Data Index: 409206 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9351. Min Act: -0.0001

Data Index: 1105495 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0803. Min Act: -0.0001

Data Index: 351061 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9898. Min Act: -0.0001

Data Index: 1071787 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8445. Min Act: -0.0001

Data Index: 1159172 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.1053. Min Act: -0.0001

Data Index: 561725 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8408. Min Act: -0.0001

Data Index: 988587 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8575. Min Act: -0.0001

Data Index: 363473 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9851. Min Act: -0.0001

Data Index: 292044 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9340. Min Act: -0.0001

Data Index: 796598 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9365. Min Act: -0.0001

Data Index: 277986 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0384. Min Act: -0.0001

Data Index: 585874 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0556. Min Act: -0.0001

Data Index: 554706 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9164. Min Act: -0.0001

Data Index: 644222 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7667. Min Act: -0.0001

Data Index: 30183 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7654. Min Act: -0.0001

Data Index: 391490 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7822. Min Act: -0.0001

Data Index: 1014358 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8647. Min Act: -0.0001

Data Index: 134893 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8018. Min Act: -0.0001

Data Index: 1163460 (C4 (Web Text))

Max Activating Token Index: 239