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

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

Neuron 2925 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1117512 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1059486 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1129065 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3509. Min Act: -0.0000

Data Index: 91313 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3407. Min Act: -0.0000

Data Index: 969569 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3259. Min Act: -0.0000

Data Index: 878054 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3118. Min Act: -0.0000

Data Index: 701696 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3077. Min Act: 0.0000

Data Index: 184663 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1199787 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1113076 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1129620 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2957. Min Act: -0.0000

Data Index: 641605 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2932. Min Act: -0.0000

Data Index: 11260 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1210319 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2885. Min Act: -0.0000

Data Index: 946914 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2772. Min Act: -0.0000

Data Index: 976584 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.3044. Min Act: -0.0000

Data Index: 552400 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1354160 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2702. Min Act: -0.0000

Data Index: 633230 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.2885. Min Act: -0.0000

Data Index: 251573 (C4 (Web Text))

Max Activating Token Index: 348