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

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

Neuron 3004 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: 0.6802. Min Range: -0.6802

Max Act: 0.6802. Min Act: -0.0000

Data Index: 307527 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.6415. Min Act: -0.0000

Data Index: 913896 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1311328 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5343. Min Act: -0.0000

Data Index: 623933 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1226347 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5357. Min Act: -0.0000

Data Index: 445721 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1066633 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1479338 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1257961 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4271. Min Act: -0.0000

Data Index: 956449 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5046. Min Act: -0.0000

Data Index: 45399 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1283326 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.3868. Min Act: -0.0000

Data Index: 166212 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4248. Min Act: -0.0000

Data Index: 551126 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4114. Min Act: -0.0000

Data Index: 695804 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.3862. Min Act: -0.0000

Data Index: 658260 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1321644 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4231. Min Act: -0.0000

Data Index: 597097 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4082. Min Act: -0.0000

Data Index: 65654 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1132712 (C4 (Web Text))

Max Activating Token Index: 955