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

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

Neuron 2900 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4003. Min Act: -0.0003

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4235. Min Act: -0.0003

Data Index: 28586 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3618. Min Act: -0.0003

Data Index: 835555 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3873. Min Act: -0.0003

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3568. Min Act: -0.0003

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3791. Min Act: -0.0003

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3622. Min Act: -0.0003

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3597. Min Act: -0.0003

Data Index: 450874 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3572. Min Act: -0.0003

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3524. Min Act: -0.0003

Data Index: 708272 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3405. Min Act: -0.0003

Data Index: 919725 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3422. Min Act: -0.0003

Data Index: 458729 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3502. Min Act: -0.0003

Data Index: 239074 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3398. Min Act: -0.0003

Data Index: 428352 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3269. Min Act: -0.0003

Data Index: 199006 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3215. Min Act: -0.0003

Data Index: 1117259 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3254. Min Act: -0.0003

Data Index: 106883 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3360. Min Act: -0.0003

Data Index: 651950 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3367. Min Act: -0.0003

Data Index: 1224477 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3820. Min Act: -0.0003

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 419