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

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

Neuron 2124 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.7661. Min Act: -0.0000

Data Index: 124130 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.5979. Min Act: -0.0000

Data Index: 587200 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.4217. Min Act: -0.0000

Data Index: 76390 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.4980. Min Act: -0.0000

Data Index: 588983 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.3047. Min Act: -0.0000

Data Index: 1165504 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.3607. Min Act: -0.0001

Data Index: 1328680 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.2852. Min Act: -0.0000

Data Index: 1223531 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.1565. Min Act: -0.0000

Data Index: 360313 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.1525. Min Act: -0.0000

Data Index: 771187 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.2519. Min Act: -0.0000

Data Index: 239620 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.2527. Min Act: -0.0001

Data Index: 575450 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.1981. Min Act: -0.0000

Data Index: 1087701 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.1377. Min Act: -0.0000

Data Index: 463851 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.1159. Min Act: -0.0000

Data Index: 1325012 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.3364. Min Act: -0.0000

Data Index: 1222001 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.3360. Min Act: -0.0000

Data Index: 763396 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.0506. Min Act: -0.0000

Data Index: 99798 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.1831. Min Act: -0.0001

Data Index: 973781 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.1681. Min Act: -0.0000

Data Index: 41906 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 2.7661. Min Range: -2.7661

Max Act: 2.0684. Min Act: -0.0000

Data Index: 1359376 (C4 (Web Text))

Max Activating Token Index: 214