Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 139 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0676. Min Range: -1.0676

Max Act: 1.0676. Min Act: -0.0000

Data Index: 312513 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.0676. Min Range: -1.0676

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1131645 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.9984. Min Act: -0.0000

Data Index: 549318 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.8443. Min Act: -0.0000

Data Index: 225418 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1314144 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.8114. Min Act: -0.0000

Data Index: 480561 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1218943 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.7278. Min Act: -0.0000

Data Index: 531063 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1305300 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.7461. Min Act: -0.0000

Data Index: 593347 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1043066 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6486. Min Act: -0.0000

Data Index: 778085 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1329649 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6971. Min Act: -0.0000

Data Index: 482363 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6383. Min Act: -0.0000

Data Index: 254716 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1177664 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6213. Min Act: -0.0000

Data Index: 582581 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6012. Min Act: -0.0000

Data Index: 264261 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5917. Min Act: -0.0000

Data Index: 764686 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1137497 (C4 (Web Text))

Max Activating Token Index: 738