Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2789 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4349. Min Act: -0.0000

Data Index: 248212 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1298581 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4148. Min Act: -0.0001

Data Index: 262984 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3877. Min Act: -0.0000

Data Index: 80316 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3816. Min Act: -0.0000

Data Index: 433814 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3611. Min Act: -0.0000

Data Index: 607404 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3568. Min Act: -0.0001

Data Index: 77855 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3860. Min Act: -0.0001

Data Index: 1349080 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3630. Min Act: -0.0001

Data Index: 342744 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3716. Min Act: -0.0000

Data Index: 376904 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3467. Min Act: -0.0000

Data Index: 143548 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1144105 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3660. Min Act: -0.0000

Data Index: 19573 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3482. Min Act: -0.0000

Data Index: 429937 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1101015 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1332835 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3294. Min Act: -0.0001

Data Index: 821221 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1033654 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3116. Min Act: -0.0000

Data Index: 717118 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3478. Min Act: -0.0001

Data Index: 916392 (C4 (Web Text))

Max Activating Token Index: 205