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

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

Neuron 2132 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: 0.9096. Min Range: -0.9096

Max Act: 0.9096. Min Act: -0.0002

Data Index: 1513019 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8983. Min Act: -0.0002

Data Index: 1446906 (Python Code)

Max Activating Token Index: 278

Text #2

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8930. Min Act: -0.0002

Data Index: 1541818 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8628. Min Act: -0.0002

Data Index: 1383693 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8787. Min Act: -0.0002

Data Index: 1596810 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8630. Min Act: -0.0002

Data Index: 1411410 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8619. Min Act: -0.0002

Data Index: 1474571 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8368. Min Act: -0.0002

Data Index: 1478712 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8456. Min Act: -0.0002

Data Index: 1386651 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8164. Min Act: -0.0002

Data Index: 1400699 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8266. Min Act: -0.0002

Data Index: 1514009 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8097. Min Act: -0.0002

Data Index: 1365326 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8182. Min Act: -0.0002

Data Index: 1652651 (Python Code)

Max Activating Token Index: 138

Text #13

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8187. Min Act: -0.0002

Data Index: 1442640 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7967. Min Act: -0.0002

Data Index: 1583027 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7984. Min Act: -0.0002

Data Index: 1387933 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8279. Min Act: -0.0002

Data Index: 1378760 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7879. Min Act: -0.0002

Data Index: 1564286 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7801. Min Act: -0.0002

Data Index: 1503424 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7786. Min Act: -0.0002

Data Index: 1643355 (Python Code)

Max Activating Token Index: 136