Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 472 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2194. Min Act: -0.0006

Data Index: 1337202 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2530. Min Act: -0.0006

Data Index: 653760 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2528. Min Act: -0.0006

Data Index: 915527 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2341. Min Act: -0.0005

Data Index: 1163846 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2266. Min Act: -0.0006

Data Index: 405243 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2204. Min Act: -0.0006

Data Index: 110247 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2162. Min Act: -0.0006

Data Index: 361634 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1902. Min Act: -0.0006

Data Index: 88794 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2129. Min Act: -0.0006

Data Index: 50787 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2097. Min Act: -0.0006

Data Index: 7410 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2186. Min Act: -0.0006

Data Index: 853114 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2186. Min Act: -0.0006

Data Index: 815221 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2009. Min Act: -0.0006

Data Index: 141366 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2076. Min Act: -0.0006

Data Index: 1058192 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2136. Min Act: -0.0006

Data Index: 462909 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1978. Min Act: -0.0006

Data Index: 394604 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2046. Min Act: -0.0006

Data Index: 219069 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1970. Min Act: -0.0006

Data Index: 1198488 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1894. Min Act: -0.0006

Data Index: 595464 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1877. Min Act: -0.0006

Data Index: 620576 (C4 (Web Text))

Max Activating Token Index: 477