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

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

Neuron 3454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2719. Min Act: -0.0000

Data Index: 907873 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2488. Min Act: 0.0000

Data Index: 624126 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2497. Min Act: -0.0000

Data Index: 474085 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2477. Min Act: -0.0000

Data Index: 186882 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1355370 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2304. Min Act: -0.0001

Data Index: 834031 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2309. Min Act: -0.0001

Data Index: 309705 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2291. Min Act: -0.0000

Data Index: 40872 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2114. Min Act: -0.0000

Data Index: 939436 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2190. Min Act: -0.0001

Data Index: 459194 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2104. Min Act: -0.0001

Data Index: 113419 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2030. Min Act: -0.0000

Data Index: 286352 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2222. Min Act: -0.0000

Data Index: 772146 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1048315 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2117. Min Act: -0.0001

Data Index: 85349 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1144767 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1104455 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1243367 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2019. Min Act: -0.0000

Data Index: 813479 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2012. Min Act: -0.0001

Data Index: 121878 (C4 (Web Text))

Max Activating Token Index: 415