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

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

Neuron 2694 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: 0.2870. Min Range: -0.2870

Max Act: 0.2828. Min Act: -0.0001

Data Index: 570476 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2756. Min Act: -0.0001

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2706. Min Act: -0.0001

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2870. Min Act: -0.0001

Data Index: 670376 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2794. Min Act: -0.0001

Data Index: 427886 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2675. Min Act: -0.0001

Data Index: 1220645 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2606. Min Act: -0.0001

Data Index: 99109 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2525. Min Act: -0.0001

Data Index: 1081922 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2543. Min Act: -0.0001

Data Index: 963494 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2521. Min Act: -0.0001

Data Index: 691474 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2481. Min Act: -0.0001

Data Index: 950189 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2467. Min Act: -0.0001

Data Index: 702828 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2380. Min Act: -0.0001

Data Index: 731039 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2365. Min Act: -0.0001

Data Index: 359211 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1003016 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2249. Min Act: -0.0001

Data Index: 454273 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2306. Min Act: -0.0001

Data Index: 1159192 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2315. Min Act: -0.0001

Data Index: 20206 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2205. Min Act: -0.0001

Data Index: 23752 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2277. Min Act: -0.0001

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 76