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

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

Neuron 3634 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: 3.1983. Min Range: -3.1983

Max Act: 3.1983. Min Act: -0.0001

Data Index: 757784 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.7803. Min Act: -0.0000

Data Index: 521505 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.8548. Min Act: -0.0000

Data Index: 59350 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.9323. Min Act: -0.0000

Data Index: 148442 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.6412. Min Act: -0.0000

Data Index: 344240 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.9541. Min Act: -0.0001

Data Index: 425727 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.6512. Min Act: -0.0000

Data Index: 674553 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 3.1983. Min Range: -3.1983

Max Act: 3.0593. Min Act: -0.0000

Data Index: 689935 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.7307. Min Act: -0.0000

Data Index: 336207 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.3582. Min Act: -0.0000

Data Index: 675365 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.3012. Min Act: -0.0001

Data Index: 923303 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 3.1983. Min Range: -3.1983

Max Act: 1.9754. Min Act: -0.0000

Data Index: 1295253 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.3399. Min Act: -0.0000

Data Index: 11694 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.2409. Min Act: -0.0000

Data Index: 35027 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.1395. Min Act: -0.0000

Data Index: 221062 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.2286. Min Act: -0.0000

Data Index: 443898 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.1921. Min Act: -0.0001

Data Index: 1075534 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.2134. Min Act: -0.0000

Data Index: 286758 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.0891. Min Act: -0.0000

Data Index: 1088426 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 3.1983. Min Range: -3.1983

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1100766 (C4 (Web Text))

Max Activating Token Index: 68