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

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

Neuron 2491 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: 0.1089. Min Range: -0.1089

Max Act: 0.1087. Min Act: -0.0001

Data Index: 483570 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0001

Data Index: 382521 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1043. Min Act: -0.0001

Data Index: 754285 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1466749 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1032. Min Act: -0.0001

Data Index: 746087 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1060. Min Act: -0.0001

Data Index: 937657 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1602731 (Python Code)

Max Activating Token Index: 193

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1418983 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1551724 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1013. Min Act: -0.0001

Data Index: 862965 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1498435 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1627228 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1446672 (Python Code)

Max Activating Token Index: 164

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1517532 (Python Code)

Max Activating Token Index: 137

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1468753 (Python Code)

Max Activating Token Index: 596

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1374094 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1619388 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1510240 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0980. Min Act: -0.0001

Data Index: 566378 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1651270 (Python Code)

Max Activating Token Index: 125