Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1614 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.6473. Min Act: -0.0000

Data Index: 188084 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.4853. Min Act: -0.0000

Data Index: 1309659 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1484885 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1331827 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.8907. Min Act: -0.0000

Data Index: 569265 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.9096. Min Act: -0.0000

Data Index: 813782 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1412164 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.8352. Min Act: -0.0000

Data Index: 478459 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.8786. Min Act: -0.0000

Data Index: 872703 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.9268. Min Act: -0.0000

Data Index: 278888 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.8516. Min Act: -0.0000

Data Index: 401954 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.8356. Min Act: -0.0000

Data Index: 526912 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.7372. Min Act: -0.0000

Data Index: 196212 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1395040 (Python Code)

Max Activating Token Index: 443

Text #14

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.7918. Min Act: -0.0000

Data Index: 366548 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.7910. Min Act: -0.0000

Data Index: 693911 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.7848. Min Act: -0.0000

Data Index: 47218 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1359012 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.7745. Min Act: -0.0000

Data Index: 173735 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.6473. Min Range: -1.6473

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1607937 (Python Code)

Max Activating Token Index: 775