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

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

Neuron 781 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1355245 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1330139 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1084345 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0725. Min Act: -0.0002

Data Index: 695619 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0728. Min Act: -0.0002

Data Index: 336160 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1159728 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0620. Min Act: -0.0002

Data Index: 340726 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1263598 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0637. Min Act: -0.0002

Data Index: 437739 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1082705 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0484. Min Act: -0.0002

Data Index: 254548 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1219783 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0425. Min Act: -0.0002

Data Index: 193762 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0473. Min Act: -0.0002

Data Index: 699533 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0393. Min Act: -0.0002

Data Index: 680123 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0432. Min Act: -0.0002

Data Index: 311873 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1292314 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1000113 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1263136 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0410. Min Act: -0.0002

Data Index: 661921 (C4 (Web Text))

Max Activating Token Index: 988