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

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

Neuron 5537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.1041. Min Act: -0.0000

Data Index: 62766 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.4620. Min Act: -0.0000

Data Index: 507751 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.5241. Min Act: -0.0001

Data Index: 1015392 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.5249. Min Act: -0.0001

Data Index: 1070919 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.3027. Min Act: -0.0001

Data Index: 1113785 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.2908. Min Act: -0.0000

Data Index: 785389 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.0845. Min Act: -0.0000

Data Index: 429599 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.0828. Min Act: -0.0000

Data Index: 1237286 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.4415. Min Act: -0.0001

Data Index: 1262189 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.2527. Min Act: -0.0001

Data Index: 347726 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 6.5249. Min Range: -6.5249

Max Act: 5.6341. Min Act: -0.0001

Data Index: 898430 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 6.5249. Min Range: -6.5249

Max Act: 5.9898. Min Act: -0.0000

Data Index: 434301 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.1663. Min Act: -0.0000

Data Index: 1215132 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 6.5249. Min Range: -6.5249

Max Act: 5.9413. Min Act: -0.0000

Data Index: 137246 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 6.5249. Min Range: -6.5249

Max Act: 5.9658. Min Act: -0.0001

Data Index: 1043107 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 6.5249. Min Range: -6.5249

Max Act: 5.9312. Min Act: -0.0001

Data Index: 105962 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.1696. Min Act: -0.0000

Data Index: 1012494 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.2885. Min Act: -0.0000

Data Index: 2321 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 6.5249. Min Range: -6.5249

Max Act: 6.2864. Min Act: -0.0000

Data Index: 269515 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 6.5249. Min Range: -6.5249

Max Act: 5.8909. Min Act: -0.0000

Data Index: 44836 (C4 (Web Text))

Max Activating Token Index: 917