Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.4387. Min Act: -0.0001

Data Index: 1246022 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.2265. Min Act: -0.0001

Data Index: 848579 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.3003. Min Act: -0.0001

Data Index: 718433 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1836. Min Act: -0.0001

Data Index: 1007036 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1621. Min Act: -0.0001

Data Index: 608261 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1802. Min Act: -0.0001

Data Index: 917163 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.2081. Min Act: -0.0001

Data Index: 1328904 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1150. Min Act: -0.0001

Data Index: 1300512 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1394. Min Act: -0.0001

Data Index: 1225 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1147. Min Act: -0.0001

Data Index: 272815 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.1356. Min Act: -0.0001

Data Index: 207219 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0919. Min Act: -0.0001

Data Index: 77149 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0098. Min Act: -0.0001

Data Index: 449900 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0384. Min Act: -0.0001

Data Index: 65449 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0304. Min Act: -0.0001

Data Index: 185614 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0566. Min Act: -0.0001

Data Index: 437970 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0512. Min Act: -0.0001

Data Index: 307305 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.4387. Min Range: -1.4387

Max Act: 1.0023. Min Act: -0.0001

Data Index: 295340 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9624. Min Act: -0.0001

Data Index: 695721 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.4387. Min Range: -1.4387

Max Act: 0.9880. Min Act: -0.0001

Data Index: 720315 (C4 (Web Text))

Max Activating Token Index: 653