Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2727 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2374. Min Act: -0.0001

Data Index: 969053 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2319. Min Act: -0.0001

Data Index: 266188 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1301061 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2208. Min Act: -0.0001

Data Index: 461451 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2184. Min Act: -0.0001

Data Index: 446514 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2064. Min Act: -0.0001

Data Index: 150396 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1235636 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1045575 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2092. Min Act: -0.0001

Data Index: 604974 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2034. Min Act: -0.0001

Data Index: 201808 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2015. Min Act: -0.0001

Data Index: 538124 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1163448 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1045231 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1929. Min Act: -0.0001

Data Index: 553469 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1990. Min Act: -0.0001

Data Index: 338812 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1914. Min Act: -0.0001

Data Index: 830935 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1854. Min Act: -0.0001

Data Index: 911319 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.2029. Min Act: -0.0001

Data Index: 682690 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1965. Min Act: -0.0001

Data Index: 321995 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.2374. Min Range: -0.2374

Max Act: 0.1893. Min Act: -0.0001

Data Index: 424059 (C4 (Web Text))

Max Activating Token Index: 493