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

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

Neuron 1761 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1293702 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1311610 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1258813 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7891. Min Act: -0.0001

Data Index: 825165 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.8109. Min Act: -0.0000

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.8089. Min Act: -0.0000

Data Index: 437136 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7334. Min Act: -0.0001

Data Index: 967200 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7282. Min Act: -0.0000

Data Index: 980268 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.8318. Min Act: -0.0000

Data Index: 626017 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.8004. Min Act: -0.0001

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1134797 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7669. Min Act: -0.0000

Data Index: 701243 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7375. Min Act: -0.0000

Data Index: 141388 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1193874 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7308. Min Act: -0.0000

Data Index: 402125 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7505. Min Act: -0.0001

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.6796. Min Act: -0.0000

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7186. Min Act: -0.0000

Data Index: 292866 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7165. Min Act: -0.0001

Data Index: 878003 (C4 (Web Text))

Max Activating Token Index: 682