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

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

Neuron 5176 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.7087. Min Act: -0.0000

Data Index: 845630 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.6519. Min Act: -0.0000

Data Index: 203467 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.4027. Min Act: -0.0000

Data Index: 822987 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1002097 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2290. Min Act: -0.0000

Data Index: 6174 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.0481. Min Act: -0.0000

Data Index: 809448 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.0634. Min Act: -0.0000

Data Index: 880476 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.1021. Min Act: -0.0000

Data Index: 319719 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1121847 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1233599 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9128. Min Act: -0.0000

Data Index: 921030 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1044317 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9465. Min Act: -0.0000

Data Index: 647731 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1129480 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9339. Min Act: -0.0000

Data Index: 83005 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1310150 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1068559 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9668. Min Act: -0.0000

Data Index: 200404 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.8561. Min Act: -0.0000

Data Index: 241099 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.8245. Min Act: -0.0000

Data Index: 821778 (C4 (Web Text))

Max Activating Token Index: 168