Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1078 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2921. Min Act: -0.0000

Data Index: 669898 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1123040 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2730. Min Act: -0.0000

Data Index: 251313 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2862. Min Act: -0.0000

Data Index: 486558 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2761. Min Act: -0.0001

Data Index: 1084574 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2725. Min Act: -0.0000

Data Index: 779616 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2606. Min Act: -0.0001

Data Index: 73165 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2696. Min Act: -0.0000

Data Index: 933329 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1036526 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1255054 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2647. Min Act: -0.0000

Data Index: 536378 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1095533 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2640. Min Act: -0.0000

Data Index: 331788 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1350007 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2638. Min Act: -0.0000

Data Index: 638306 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2446. Min Act: -0.0000

Data Index: 700236 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2525. Min Act: -0.0001

Data Index: 94856 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1199426 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2593. Min Act: -0.0000

Data Index: 798721 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1230282 (C4 (Web Text))

Max Activating Token Index: 1004