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

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

Neuron 3167 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1965. Min Act: -0.0001

Data Index: 471944 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1819. Min Act: -0.0001

Data Index: 377923 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1868. Min Act: -0.0001

Data Index: 589341 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1743. Min Act: -0.0001

Data Index: 304300 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1784. Min Act: -0.0001

Data Index: 167529 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1540. Min Act: -0.0001

Data Index: 304632 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1130340 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1322030 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1479. Min Act: -0.0001

Data Index: 97223 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1516. Min Act: -0.0001

Data Index: 438920 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1066378 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1307. Min Act: -0.0001

Data Index: 621994 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1397. Min Act: -0.0001

Data Index: 936264 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1207. Min Act: -0.0001

Data Index: 742820 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1041514 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1310721 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1371. Min Act: -0.0001

Data Index: 708836 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1018893 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1267. Min Act: -0.0001

Data Index: 83243 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1331. Min Act: -0.0001

Data Index: 282898 (C4 (Web Text))

Max Activating Token Index: 888