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

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

Neuron 5356 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1531764 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1538515 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1478616 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1386617 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1573149 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1650148 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1558661 (Python Code)

Max Activating Token Index: 269

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1379778 (Python Code)

Max Activating Token Index: 401

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1457585 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1548120 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1581082 (Python Code)

Max Activating Token Index: 1010

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1365948 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1571390 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1583834 (Python Code)

Max Activating Token Index: 862

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1464408 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1548610 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1452844 (Python Code)

Max Activating Token Index: 520

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1461477 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1390235 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1466435 (Python Code)

Max Activating Token Index: 855