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

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

Neuron 1423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.8105. Min Act: -0.0000

Data Index: 822662 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.6180. Min Act: -0.0000

Data Index: 613375 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.4506. Min Act: -0.0000

Data Index: 736761 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1135762 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.4204. Min Act: -0.0000

Data Index: 685807 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2971. Min Act: -0.0000

Data Index: 972713 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2793. Min Act: -0.0000

Data Index: 296286 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3657. Min Act: -0.0000

Data Index: 148508 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.1900. Min Act: -0.0000

Data Index: 483163 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1318050 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1019919 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3424. Min Act: -0.0000

Data Index: 1034221 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1330581 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1106769 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3006. Min Act: -0.0000

Data Index: 976142 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1060980 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1124346 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3073. Min Act: -0.0000

Data Index: 359936 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2996. Min Act: -0.0000

Data Index: 553046 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.1429. Min Act: -0.0000

Data Index: 1319186 (C4 (Web Text))

Max Activating Token Index: 793