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

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

Neuron 4976 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: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0000

Data Index: 542091 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0109. Min Act: -0.0001

Data Index: 1581489 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0100. Min Act: -0.0001

Data Index: 1575964 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0097. Min Act: -0.0000

Data Index: 841480 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0084. Min Act: -0.0001

Data Index: 390769 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0094. Min Act: -0.0000

Data Index: 1466624 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0089. Min Act: -0.0001

Data Index: 785916 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0094. Min Act: -0.0001

Data Index: 460496 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0096. Min Act: -0.0000

Data Index: 259789 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0088. Min Act: -0.0001

Data Index: 100533 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1174620 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0087. Min Act: -0.0001

Data Index: 984817 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0089. Min Act: -0.0001

Data Index: 1567670 (Python Code)

Max Activating Token Index: 239

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0086. Min Act: -0.0000

Data Index: 975514 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0090. Min Act: -0.0001

Data Index: 361954 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0091. Min Act: -0.0001

Data Index: 1400572 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0081. Min Act: -0.0000

Data Index: 1289436 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0085. Min Act: -0.0001

Data Index: 1597297 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0087. Min Act: -0.0000

Data Index: 1195902 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0080. Min Act: -0.0001

Data Index: 1411807 (Python Code)

Max Activating Token Index: 301