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

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

Neuron 271 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1501380 (Python Code)

Max Activating Token Index: 593

Text #1

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.3550. Min Act: -0.0000

Data Index: 1527229 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.2887. Min Act: -0.0000

Data Index: 1409942 (Python Code)

Max Activating Token Index: 157

Text #3

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1549344 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1537647 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1413006 (Python Code)

Max Activating Token Index: 856

Text #6

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1536276 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1254428 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9070. Min Act: -0.0000

Data Index: 467125 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.8328. Min Act: -0.0000

Data Index: 629584 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1374221 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.8192. Min Act: -0.0000

Data Index: 617025 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1577780 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.7840. Min Act: -0.0000

Data Index: 58022 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.7936. Min Act: -0.0000

Data Index: 725524 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1375860 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.7771. Min Act: -0.0000

Data Index: 502886 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1262025 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1552756 (Python Code)

Max Activating Token Index: 863

Text #19

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.7639. Min Act: -0.0000

Data Index: 118609 (C4 (Web Text))

Max Activating Token Index: 765