Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4925 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.1402. Min Range: -5.1402

Max Act: 5.1402. Min Act: -0.0001

Data Index: 1281942 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 5.1402. Min Range: -5.1402

Max Act: 5.0497. Min Act: -0.0001

Data Index: 365896 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.8004. Min Act: -0.0001

Data Index: 824091 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.4891. Min Act: -0.0001

Data Index: 87198 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.2016. Min Act: -0.0001

Data Index: 1074842 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.4758. Min Act: -0.0001

Data Index: 974 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.2605. Min Act: -0.0001

Data Index: 118 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.7187. Min Act: -0.0001

Data Index: 95122 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.3471. Min Act: -0.0001

Data Index: 612113 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.1382. Min Act: -0.0000

Data Index: 1161434 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.8789. Min Act: -0.0001

Data Index: 1197306 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.2023. Min Act: -0.0001

Data Index: 696565 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 5.1402. Min Range: -5.1402

Max Act: 4.1796. Min Act: -0.0001

Data Index: 158103 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.8068. Min Act: -0.0001

Data Index: 1188453 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.6353. Min Act: -0.0001

Data Index: 280739 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.8854. Min Act: -0.0001

Data Index: 62393 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.7319. Min Act: -0.0001

Data Index: 96834 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.5189. Min Act: -0.0001

Data Index: 73343 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.8521. Min Act: -0.0000

Data Index: 1091884 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 5.1402. Min Range: -5.1402

Max Act: 3.6503. Min Act: -0.0001

Data Index: 138241 (C4 (Web Text))

Max Activating Token Index: 501