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

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

Neuron 893 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: 2.0566. Min Range: -2.0566

Max Act: 2.0566. Min Act: -0.0000

Data Index: 348489 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.4952. Min Act: -0.0000

Data Index: 876612 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.4908. Min Act: 0.0001

Data Index: 791061 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2507. Min Act: -0.0000

Data Index: 372865 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.3912. Min Act: -0.0000

Data Index: 103903 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.4035. Min Act: -0.0000

Data Index: 951137 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.3522. Min Act: -0.0000

Data Index: 386996 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1335152 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.4313. Min Act: -0.0000

Data Index: 386661 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.3786. Min Act: -0.0000

Data Index: 876516 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1338144 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.3868. Min Act: -0.0000

Data Index: 330397 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2965. Min Act: -0.0000

Data Index: 236212 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.1460. Min Act: 0.0000

Data Index: 858358 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2795. Min Act: -0.0000

Data Index: 682854 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.3700. Min Act: -0.0000

Data Index: 270148 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2144. Min Act: -0.0000

Data Index: 636178 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1127147 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2714. Min Act: -0.0000

Data Index: 122862 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 2.0566. Min Range: -2.0566

Max Act: 1.2688. Min Act: -0.0000

Data Index: 555263 (C4 (Web Text))

Max Activating Token Index: 483