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

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

Neuron 3384 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: 0.3601. Min Range: -0.3601

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1359957 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1496789 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.3329. Min Act: -0.0000

Data Index: 896879 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1255186 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.3090. Min Act: -0.0000

Data Index: 648942 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2899. Min Act: -0.0000

Data Index: 805967 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2719. Min Act: -0.0000

Data Index: 238362 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2801. Min Act: -0.0000

Data Index: 110618 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2661. Min Act: -0.0000

Data Index: 656317 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2661. Min Act: -0.0000

Data Index: 634872 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2473. Min Act: -0.0000

Data Index: 751488 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1104347 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2734. Min Act: -0.0000

Data Index: 183161 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2895. Min Act: -0.0000

Data Index: 325198 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2613. Min Act: -0.0000

Data Index: 324945 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1164183 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1297735 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2708. Min Act: -0.0000

Data Index: 215242 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1315221 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.3601. Min Range: -0.3601

Max Act: 0.2654. Min Act: -0.0000

Data Index: 974330 (C4 (Web Text))

Max Activating Token Index: 1004