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

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

Neuron 4086 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0001

Data Index: 509864 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3605. Min Act: -0.0001

Data Index: 551198 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3562. Min Act: -0.0001

Data Index: 472304 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3540. Min Act: -0.0001

Data Index: 655957 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3385. Min Act: -0.0001

Data Index: 616594 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3497. Min Act: -0.0001

Data Index: 1237966 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3489. Min Act: -0.0001

Data Index: 632569 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3428. Min Act: -0.0001

Data Index: 128876 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3319. Min Act: -0.0001

Data Index: 817202 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3420. Min Act: -0.0001

Data Index: 220770 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3655. Min Act: -0.0001

Data Index: 500170 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3367. Min Act: -0.0001

Data Index: 531031 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3300. Min Act: -0.0001

Data Index: 1202020 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3337. Min Act: -0.0001

Data Index: 710351 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3217. Min Act: -0.0001

Data Index: 846384 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3213. Min Act: -0.0001

Data Index: 338037 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3293. Min Act: -0.0001

Data Index: 178294 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3267. Min Act: -0.0001

Data Index: 1028306 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3353. Min Act: -0.0001

Data Index: 31954 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3137. Min Act: -0.0001

Data Index: 593632 (C4 (Web Text))

Max Activating Token Index: 614