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

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

Neuron 3281 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: 0.1352. Min Range: -0.1352

Max Act: 0.1352. Min Act: -0.0001

Data Index: 922421 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1179709 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1198152 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1236. Min Act: -0.0001

Data Index: 753186 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0973. Min Act: -0.0001

Data Index: 438164 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1113. Min Act: -0.0001

Data Index: 574102 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1067. Min Act: -0.0001

Data Index: 900136 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1081. Min Act: -0.0001

Data Index: 598265 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1018. Min Act: -0.0001

Data Index: 332700 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1042. Min Act: -0.0001

Data Index: 807409 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0989. Min Act: -0.0001

Data Index: 47820 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1278077 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0978. Min Act: -0.0001

Data Index: 304386 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1165374 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1004665 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0978. Min Act: -0.0001

Data Index: 193014 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1314432 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0918. Min Act: -0.0001

Data Index: 754479 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0951. Min Act: -0.0001

Data Index: 877404 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1086506 (C4 (Web Text))

Max Activating Token Index: 898