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

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

Neuron 3672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.7748. Min Act: -0.0000

Data Index: 1471101 (Python Code)

Max Activating Token Index: 905

Text #1

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.3069. Min Act: -0.0000

Data Index: 1547833 (Python Code)

Max Activating Token Index: 253

Text #2

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.4001. Min Act: -0.0000

Data Index: 1364391 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.5831. Min Act: -0.0001

Data Index: 1446280 (Python Code)

Max Activating Token Index: 864

Text #4

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.0985. Min Act: -0.0000

Data Index: 1587887 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.5522. Min Act: -0.0001

Data Index: 1233188 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.4210. Min Act: -0.0000

Data Index: 1417052 (Python Code)

Max Activating Token Index: 374

Text #7

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.8454. Min Act: -0.0001

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.6773. Min Act: -0.0000

Data Index: 1614625 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.0963. Min Act: -0.0001

Data Index: 1056840 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.5171. Min Act: -0.0000

Data Index: 1609937 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.0063. Min Act: -0.0001

Data Index: 1445226 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.8473. Min Act: -0.0000

Data Index: 1631017 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.8035. Min Act: -0.0001

Data Index: 1467441 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.0934. Min Act: -0.0001

Data Index: 1560626 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.2089. Min Act: -0.0000

Data Index: 1578723 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.7983. Min Act: -0.0000

Data Index: 1541986 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.9422. Min Act: -0.0000

Data Index: 1056876 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 4.7748. Min Range: -4.7748

Max Act: 4.0957. Min Act: -0.0000

Data Index: 1434531 (Python Code)

Max Activating Token Index: 425

Text #19

Max Range: 4.7748. Min Range: -4.7748

Max Act: 3.7172. Min Act: -0.0001

Data Index: 1646066 (Python Code)

Max Activating Token Index: 397