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

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

Neuron 1804 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.9782. Min Act: -0.0000

Data Index: 987454 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 6.1462. Min Range: -6.1462

Max Act: 6.1462. Min Act: -0.0000

Data Index: 1249112 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 6.1462. Min Range: -6.1462

Max Act: 6.1360. Min Act: -0.0000

Data Index: 573674 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.7409. Min Act: -0.0000

Data Index: 61560 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.8789. Min Act: -0.0000

Data Index: 447620 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.9685. Min Act: -0.0000

Data Index: 114076 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.7899. Min Act: -0.0000

Data Index: 832754 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.7677. Min Act: -0.0000

Data Index: 256768 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.7711. Min Act: -0.0000

Data Index: 517363 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.8555. Min Act: -0.0000

Data Index: 465436 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.7997. Min Act: -0.0000

Data Index: 1133545 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.8040. Min Act: -0.0000

Data Index: 147287 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.5989. Min Act: -0.0000

Data Index: 178605 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.1895. Min Act: -0.0000

Data Index: 1221835 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.3145. Min Act: -0.0000

Data Index: 223146 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.0679. Min Act: -0.0000

Data Index: 1178142 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.2454. Min Act: -0.0000

Data Index: 758887 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.2269. Min Act: -0.0000

Data Index: 194104 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.1980. Min Act: -0.0000

Data Index: 758814 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 6.1462. Min Range: -6.1462

Max Act: 5.3851. Min Act: -0.0000

Data Index: 328000 (C4 (Web Text))

Max Activating Token Index: 697