Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3292 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3390. Min Act: -0.0000

Data Index: 312945 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3464. Min Act: -0.0000

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1285002 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3317. Min Act: -0.0000

Data Index: 731424 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3243. Min Act: -0.0000

Data Index: 803839 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3324. Min Act: -0.0000

Data Index: 64003 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3253. Min Act: -0.0000

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3109. Min Act: -0.0000

Data Index: 353993 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3145. Min Act: -0.0000

Data Index: 566880 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1133353 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3058. Min Act: -0.0000

Data Index: 984261 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2954. Min Act: -0.0000

Data Index: 677470 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2986. Min Act: -0.0000

Data Index: 24361 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3011. Min Act: -0.0000

Data Index: 523217 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1018386 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2979. Min Act: -0.0000

Data Index: 333512 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2846. Min Act: -0.0000

Data Index: 219582 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1535250 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1177911 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2929. Min Act: -0.0000

Data Index: 145468 (C4 (Web Text))

Max Activating Token Index: 197