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

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

Neuron 982 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: 2.0280. Min Range: -2.0280

Max Act: 2.0280. Min Act: -0.0000

Data Index: 760966 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.8185. Min Act: -0.0000

Data Index: 992472 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.8229. Min Act: -0.0000

Data Index: 1092108 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.8637. Min Act: -0.0000

Data Index: 560788 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.6953. Min Act: -0.0000

Data Index: 555021 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.6173. Min Act: -0.0000

Data Index: 1207282 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.5546. Min Act: -0.0000

Data Index: 1328162 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.4691. Min Act: -0.0000

Data Index: 982754 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.5669. Min Act: -0.0000

Data Index: 848169 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.4767. Min Act: -0.0000

Data Index: 648691 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.4544. Min Act: -0.0000

Data Index: 884099 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.5010. Min Act: -0.0000

Data Index: 865020 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.4046. Min Act: -0.0000

Data Index: 1340619 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.4513. Min Act: -0.0000

Data Index: 332621 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1195283 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.2144. Min Act: -0.0000

Data Index: 1258268 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.2741. Min Act: -0.0000

Data Index: 47836 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.1999. Min Act: -0.0000

Data Index: 35258 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.3370. Min Act: -0.0000

Data Index: 461817 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 2.0280. Min Range: -2.0280

Max Act: 1.2553. Min Act: -0.0000

Data Index: 1272654 (C4 (Web Text))

Max Activating Token Index: 447