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

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

Neuron 505 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7963. Min Act: -0.0000

Data Index: 740667 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.5679. Min Act: -0.0000

Data Index: 497794 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.5413. Min Act: -0.0000

Data Index: 1124724 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.4040. Min Act: -0.0000

Data Index: 1224183 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.4003. Min Act: -0.0000

Data Index: 119899 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6475. Min Act: -0.0000

Data Index: 381638 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.3576. Min Act: -0.0000

Data Index: 355836 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.4350. Min Act: -0.0000

Data Index: 626524 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.4060. Min Act: -0.0000

Data Index: 59669 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.2770. Min Act: -0.0000

Data Index: 667998 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.3751. Min Act: -0.0000

Data Index: 748363 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.2126. Min Act: -0.0000

Data Index: 822290 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.2153. Min Act: -0.0000

Data Index: 225989 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.3343. Min Act: -0.0000

Data Index: 1056242 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.3036. Min Act: -0.0000

Data Index: 605244 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.1755. Min Act: -0.0000

Data Index: 219008 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.1692. Min Act: -0.0000

Data Index: 845763 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.3769. Min Act: -0.0000

Data Index: 1230985 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.1400. Min Act: -0.0000

Data Index: 882879 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.2330. Min Act: -0.0000

Data Index: 10081 (C4 (Web Text))

Max Activating Token Index: 132