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

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

Neuron 5859 in Layer 0

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: 0.1130. Min Range: -0.1130

Max Act: 0.1130. Min Act: -0.0001

Data Index: 361413 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1406379 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1637301 (Python Code)

Max Activating Token Index: 515

Text #3

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1632523 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1508298 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1480102 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1608991 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1548266 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1508291 (Python Code)

Max Activating Token Index: 439

Text #9

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1531508 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1386784 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0974. Min Act: -0.0001

Data Index: 701588 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1427507 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1575877 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1380332 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1605090 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1442684 (Python Code)

Max Activating Token Index: 770

Text #17

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1442130 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1420873 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1390811 (Python Code)

Max Activating Token Index: 18