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

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

Neuron 3815 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2322. Min Act: -0.0000

Data Index: 187438 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2246. Min Act: -0.0000

Data Index: 677365 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2425. Min Act: -0.0000

Data Index: 100228 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1164939 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2342. Min Act: -0.0000

Data Index: 189182 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2217. Min Act: -0.0001

Data Index: 538679 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2319. Min Act: -0.0000

Data Index: 381353 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1975. Min Act: -0.0000

Data Index: 888375 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2054. Min Act: -0.0000

Data Index: 683980 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2071. Min Act: -0.0000

Data Index: 82832 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2132. Min Act: -0.0000

Data Index: 804902 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2063. Min Act: -0.0000

Data Index: 218378 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2022. Min Act: -0.0001

Data Index: 87044 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2048. Min Act: -0.0001

Data Index: 976122 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1152853 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2033. Min Act: -0.0000

Data Index: 226018 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1870. Min Act: -0.0001

Data Index: 110541 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1837. Min Act: -0.0001

Data Index: 990889 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1714. Min Act: -0.0001

Data Index: 535448 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1892. Min Act: -0.0000

Data Index: 645080 (C4 (Web Text))

Max Activating Token Index: 301