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

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

Neuron 724 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3878. Min Range: -2.3878

Max Act: 2.3263. Min Act: -0.0000

Data Index: 512071 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 2.3878. Min Range: -2.3878

Max Act: 2.3878. Min Act: -0.0000

Data Index: 132008 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 2.3878. Min Range: -2.3878

Max Act: 2.1439. Min Act: -0.0000

Data Index: 472082 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 2.3878. Min Range: -2.3878

Max Act: 1.8087. Min Act: -0.0000

Data Index: 2605 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 2.3878. Min Range: -2.3878

Max Act: 1.7953. Min Act: -0.0000

Data Index: 372802 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 2.3878. Min Range: -2.3878

Max Act: 1.7838. Min Act: -0.0000

Data Index: 1008564 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 2.3878. Min Range: -2.3878

Max Act: 1.7423. Min Act: -0.0000

Data Index: 120163 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 2.3878. Min Range: -2.3878

Max Act: 1.4374. Min Act: -0.0000

Data Index: 648420 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 2.3878. Min Range: -2.3878

Max Act: 1.0695. Min Act: -0.0000

Data Index: 928749 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.8440. Min Act: -0.0000

Data Index: 87792 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1086327 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.8135. Min Act: -0.0000

Data Index: 846721 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.8029. Min Act: -0.0000

Data Index: 815815 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.8191. Min Act: -0.0000

Data Index: 81878 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.7441. Min Act: -0.0000

Data Index: 470196 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.7328. Min Act: -0.0000

Data Index: 844473 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1279943 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.7739. Min Act: -0.0000

Data Index: 421088 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.6595. Min Act: -0.0000

Data Index: 533750 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.3878. Min Range: -2.3878

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1076799 (C4 (Web Text))

Max Activating Token Index: 382