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

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

Neuron 5685 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1043163 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1531. Min Act: -0.0000

Data Index: 96807 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1477. Min Act: -0.0000

Data Index: 181270 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1060076 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1595. Min Act: -0.0000

Data Index: 955156 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1325. Min Act: -0.0000

Data Index: 10893 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1435. Min Act: -0.0000

Data Index: 266010 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1143870 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1343. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1263. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1363940 (Python Code)

Max Activating Token Index: 770

Text #11

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1232. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1557138 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1258. Min Act: -0.0000

Data Index: 436763 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1557080 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1285. Min Act: -0.0000

Data Index: 654972 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1564686 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1174420 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1207. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1548598 (Python Code)

Max Activating Token Index: 741