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

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

Neuron 2546 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6189. Min Range: -1.6189

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1634561 (Python Code)

Max Activating Token Index: 595

Text #1

Max Range: 1.6189. Min Range: -1.6189

Max Act: 1.5030. Min Act: -0.0000

Data Index: 1500354 (Python Code)

Max Activating Token Index: 929

Text #2

Max Range: 1.6189. Min Range: -1.6189

Max Act: 1.2511. Min Act: -0.0000

Data Index: 346188 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.6189. Min Range: -1.6189

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1608104 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 1.6189. Min Range: -1.6189

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1374742 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1655652 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1436830 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1513299 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1512925 (Python Code)

Max Activating Token Index: 992

Text #9

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.8145. Min Act: -0.0000

Data Index: 804028 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1526629 (Python Code)

Max Activating Token Index: 522

Text #11

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1470336 (Python Code)

Max Activating Token Index: 565

Text #12

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1554062 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1499045 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1649989 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1644046 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1496769 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.6652. Min Act: -0.0000

Data Index: 392378 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1422376 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.6189. Min Range: -1.6189

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1363157 (Python Code)

Max Activating Token Index: 140