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

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

Neuron 2616 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.5429. Min Act: -0.0001

Data Index: 793070 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.4598. Min Act: -0.0001

Data Index: 613298 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.4165. Min Act: -0.0001

Data Index: 190291 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3010. Min Act: -0.0001

Data Index: 228367 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3686. Min Act: -0.0001

Data Index: 837370 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3190. Min Act: -0.0001

Data Index: 846622 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3104. Min Act: -0.0001

Data Index: 1331225 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2581. Min Act: -0.0001

Data Index: 148900 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2807. Min Act: -0.0001

Data Index: 1324198 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3080. Min Act: -0.0001

Data Index: 1281179 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2591. Min Act: -0.0001

Data Index: 215447 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2883. Min Act: -0.0001

Data Index: 353467 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.1993. Min Act: -0.0000

Data Index: 684462 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2629. Min Act: -0.0001

Data Index: 1304166 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2595. Min Act: -0.0001

Data Index: 1346266 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.1834. Min Act: -0.0001

Data Index: 502342 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2288. Min Act: -0.0001

Data Index: 983475 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2018. Min Act: -0.0001

Data Index: 1352879 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.1386. Min Act: -0.0001

Data Index: 1125921 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.1218. Min Act: -0.0001

Data Index: 613869 (C4 (Web Text))

Max Activating Token Index: 761