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

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

Neuron 3821 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3641. Min Act: -0.0000

Data Index: 563259 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1011092 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3003. Min Act: -0.0000

Data Index: 194409 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2732. Min Act: -0.0000

Data Index: 943280 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2452. Min Act: -0.0000

Data Index: 955814 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2577. Min Act: -0.0001

Data Index: 315910 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2179. Min Act: -0.0000

Data Index: 855724 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1112410 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2535. Min Act: -0.0000

Data Index: 781178 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2349. Min Act: -0.0000

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1090465 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2443. Min Act: -0.0000

Data Index: 326677 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2319. Min Act: -0.0000

Data Index: 804446 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2487. Min Act: -0.0000

Data Index: 983430 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2375. Min Act: -0.0001

Data Index: 1208410 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2358. Min Act: -0.0000

Data Index: 902789 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2378. Min Act: -0.0000

Data Index: 423295 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1345505 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2326. Min Act: -0.0000

Data Index: 650803 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2166. Min Act: -0.0000

Data Index: 805541 (C4 (Web Text))

Max Activating Token Index: 349