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

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

Neuron 4778 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.6771. Min Act: -0.0000

Data Index: 525894 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.1205. Min Act: -0.0000

Data Index: 934127 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0768. Min Act: -0.0000

Data Index: 285047 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0545. Min Act: -0.0000

Data Index: 919869 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1434115 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0446. Min Act: -0.0000

Data Index: 667146 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1048176 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0457. Min Act: -0.0000

Data Index: 153991 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0416. Min Act: -0.0000

Data Index: 427579 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0444. Min Act: -0.0000

Data Index: 1602602 (Python Code)

Max Activating Token Index: 466

Text #10

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1697 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1334581 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1181478 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0402. Min Act: -0.0000

Data Index: 980642 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0412. Min Act: -0.0000

Data Index: 1297545 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1456451 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0407. Min Act: -0.0000

Data Index: 7144 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0380. Min Act: -0.0000

Data Index: 214892 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1612131 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 0.6771. Min Range: -0.6771

Max Act: 0.0384. Min Act: -0.0000

Data Index: 850311 (C4 (Web Text))

Max Activating Token Index: 106