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

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

Neuron 6003 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1018953 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.6823. Min Act: -0.0000

Data Index: 5 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1311099 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1236016 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1318458 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1040146 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1126589 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.4875. Min Act: -0.0000

Data Index: 876148 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.4729. Min Act: -0.0000

Data Index: 130985 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.4215. Min Act: -0.0000

Data Index: 300802 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1123378 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.4142. Min Act: -0.0000

Data Index: 291057 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.4022. Min Act: -0.0000

Data Index: 876485 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.3739. Min Act: -0.0000

Data Index: 514312 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.3445. Min Act: -0.0000

Data Index: 337902 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1217212 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.3900. Min Act: -0.0000

Data Index: 372185 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.3782. Min Act: 0.0000

Data Index: 1065058 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1066114 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.7367. Min Range: -0.7367

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1351724 (C4 (Web Text))

Max Activating Token Index: 261