Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2328 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.3015. Min Act: -0.0001

Data Index: 285505 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.3342. Min Act: -0.0001

Data Index: 211884 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2745. Min Act: -0.0001

Data Index: 494638 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2847. Min Act: -0.0001

Data Index: 941381 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.3101. Min Act: -0.0001

Data Index: 1518149 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2778. Min Act: -0.0001

Data Index: 697888 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.3027. Min Act: -0.0001

Data Index: 814691 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1239870 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1448822 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1206785 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2815. Min Act: -0.0001

Data Index: 816923 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2601. Min Act: -0.0001

Data Index: 805330 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2556. Min Act: -0.0001

Data Index: 160629 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1594770 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1442598 (Python Code)

Max Activating Token Index: 956

Text #15

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2770. Min Act: -0.0001

Data Index: 1408657 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1588630 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2429. Min Act: -0.0001

Data Index: 336147 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1201662 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1338924 (C4 (Web Text))

Max Activating Token Index: 984