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

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

Neuron 4080 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.6549. Min Act: -0.0001

Data Index: 1546441 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.4344. Min Act: -0.0001

Data Index: 1534114 (Python Code)

Max Activating Token Index: 764

Text #2

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.5195. Min Act: -0.0001

Data Index: 1592735 (Python Code)

Max Activating Token Index: 929

Text #3

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.4397. Min Act: -0.0001

Data Index: 1626589 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.4237. Min Act: -0.0001

Data Index: 1471928 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.4618. Min Act: -0.0001

Data Index: 1593799 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.3291. Min Act: -0.0001

Data Index: 493741 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.5779. Min Act: -0.0001

Data Index: 1431170 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.4112. Min Act: -0.0001

Data Index: 1603181 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2354. Min Act: -0.0000

Data Index: 1519280 (Python Code)

Max Activating Token Index: 675

Text #10

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2530. Min Act: -0.0001

Data Index: 1586511 (Python Code)

Max Activating Token Index: 81

Text #11

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2788. Min Act: -0.0001

Data Index: 1620564 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2027. Min Act: -0.0000

Data Index: 1557372 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2860. Min Act: -0.0001

Data Index: 422646 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2759. Min Act: -0.0000

Data Index: 1550843 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.1941. Min Act: -0.0001

Data Index: 1369972 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2574. Min Act: -0.0001

Data Index: 1553404 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2153. Min Act: -0.0001

Data Index: 1437201 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1360252 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 1.6549. Min Range: -1.6549

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1590675 (Python Code)

Max Activating Token Index: 38