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

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

Neuron 1120 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: 0.4387. Min Range: -0.4387

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1090972 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3673. Min Act: -0.0001

Data Index: 1093732 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3280. Min Act: -0.0001

Data Index: 1064192 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3178. Min Act: -0.0001

Data Index: 355632 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2473. Min Act: -0.0001

Data Index: 55063 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3104. Min Act: -0.0001

Data Index: 32191 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2883. Min Act: -0.0000

Data Index: 712801 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2696. Min Act: -0.0001

Data Index: 777317 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2693. Min Act: -0.0000

Data Index: 691207 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2653. Min Act: -0.0000

Data Index: 854834 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2615. Min Act: -0.0001

Data Index: 1257119 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2817. Min Act: -0.0001

Data Index: 1230786 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1097723 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2677. Min Act: -0.0001

Data Index: 990979 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2763. Min Act: -0.0001

Data Index: 204756 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2835. Min Act: -0.0001

Data Index: 358443 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2843. Min Act: -0.0001

Data Index: 192849 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2337. Min Act: -0.0001

Data Index: 1268831 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2598. Min Act: -0.0000

Data Index: 432289 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2590. Min Act: -0.0001

Data Index: 22996 (C4 (Web Text))

Max Activating Token Index: 430