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

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

Neuron 5576 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.2809. Min Act: -0.0000

Data Index: 414256 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1646548 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.1842. Min Act: -0.0000

Data Index: 325917 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1250680 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.0914. Min Act: -0.0000

Data Index: 895820 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.2148. Min Act: -0.0000

Data Index: 69776 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.0921. Min Act: -0.0000

Data Index: 1452022 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1407839 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1207252 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1638904 (Python Code)

Max Activating Token Index: 801

Text #10

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1501654 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9481. Min Act: -0.0000

Data Index: 145989 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.3381. Min Range: -1.3381

Max Act: 1.0056. Min Act: -0.0000

Data Index: 877359 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1482754 (Python Code)

Max Activating Token Index: 542

Text #14

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.8200. Min Act: -0.0000

Data Index: 659303 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9820. Min Act: -0.0000

Data Index: 334750 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1473917 (Python Code)

Max Activating Token Index: 635

Text #17

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9152. Min Act: -0.0000

Data Index: 796946 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1402653 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 1.3381. Min Range: -1.3381

Max Act: 0.8563. Min Act: -0.0000

Data Index: 445222 (C4 (Web Text))

Max Activating Token Index: 784