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

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

Neuron 3441 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.2247. Min Act: -0.0001

Data Index: 533212 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.2162. Min Act: -0.0001

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1899. Min Act: -0.0001

Data Index: 421026 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.2002. Min Act: -0.0001

Data Index: 998183 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1920. Min Act: -0.0001

Data Index: 55029 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1957. Min Act: -0.0001

Data Index: 736363 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1953. Min Act: -0.0001

Data Index: 141485 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1813. Min Act: -0.0001

Data Index: 309249 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1837. Min Act: -0.0001

Data Index: 148184 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1834. Min Act: -0.0001

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1762. Min Act: -0.0001

Data Index: 916844 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1742. Min Act: -0.0001

Data Index: 674196 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1786. Min Act: -0.0001

Data Index: 819940 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1747. Min Act: -0.0001

Data Index: 310084 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1575. Min Act: -0.0001

Data Index: 595614 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1619. Min Act: -0.0001

Data Index: 541579 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1576. Min Act: -0.0001

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1015479 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1545. Min Act: -0.0001

Data Index: 505463 (C4 (Web Text))

Max Activating Token Index: 741