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

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

Neuron 5999 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1226665 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.2555. Min Act: 0.0000

Data Index: 1109709 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0297. Min Act: -0.0000

Data Index: 143397 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1008. Min Act: -0.0000

Data Index: 676677 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0625. Min Act: -0.0000

Data Index: 270594 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1275361 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1156983 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9497. Min Act: -0.0000

Data Index: 384994 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9181. Min Act: -0.0000

Data Index: 65699 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9009. Min Act: -0.0000

Data Index: 60707 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8084. Min Act: -0.0000

Data Index: 416582 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1311935 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8491. Min Act: -0.0000

Data Index: 66224 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8045. Min Act: -0.0000

Data Index: 380609 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1300643 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1008917 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8726. Min Act: -0.0000

Data Index: 464924 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8164. Min Act: -0.0000

Data Index: 276747 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8081. Min Act: -0.0000

Data Index: 804843 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1026816 (C4 (Web Text))

Max Activating Token Index: 449