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

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

Neuron 3356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0000

Data Index: 220409 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1301241 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1507. Min Act: -0.0000

Data Index: 421726 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1519. Min Act: -0.0001

Data Index: 827052 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1419. Min Act: -0.0001

Data Index: 906820 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1124529 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1226310 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1001019 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1172610 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1360. Min Act: -0.0001

Data Index: 919484 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1268541 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1328. Min Act: -0.0001

Data Index: 364302 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1351030 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1215136 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1322. Min Act: -0.0001

Data Index: 478126 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1260. Min Act: -0.0001

Data Index: 167799 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1028554 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1251. Min Act: -0.0000

Data Index: 119185 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1128981 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1279. Min Act: -0.0001

Data Index: 159497 (C4 (Web Text))

Max Activating Token Index: 154