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

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

Neuron 2507 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.6387. Min Act: -0.0000

Data Index: 1237165 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3673. Min Act: -0.0001

Data Index: 897921 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.1510. Min Act: -0.0000

Data Index: 483890 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.8588. Min Act: -0.0000

Data Index: 584423 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.0697. Min Act: -0.0000

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.9091. Min Act: -0.0001

Data Index: 925340 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.9076. Min Act: -0.0000

Data Index: 683481 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.5408. Min Act: -0.0000

Data Index: 157187 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.7497. Min Act: -0.0000

Data Index: 556927 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.6170. Min Act: -0.0000

Data Index: 384450 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.7414. Min Act: -0.0000

Data Index: 669912 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.8402. Min Act: -0.0001

Data Index: 903544 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.8081. Min Act: -0.0000

Data Index: 411092 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.4269. Min Act: -0.0000

Data Index: 553562 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.6629. Min Act: -0.0001

Data Index: 455262 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.2678. Min Act: -0.0000

Data Index: 244195 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.4508. Min Act: -0.0001

Data Index: 1243845 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.4399. Min Act: -0.0000

Data Index: 1226715 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.5725. Min Act: -0.0000

Data Index: 43817 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 3.6387. Min Range: -3.6387

Max Act: 2.2616. Min Act: -0.0001

Data Index: 793485 (C4 (Web Text))

Max Activating Token Index: 819