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

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

Neuron 3500 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: 0.7110. Min Range: -0.7110

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1040067 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6532. Min Act: -0.0001

Data Index: 492885 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6256. Min Act: -0.0001

Data Index: 66632 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6355. Min Act: -0.0001

Data Index: 1218261 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5860. Min Act: -0.0001

Data Index: 341689 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5681. Min Act: -0.0001

Data Index: 375427 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6076. Min Act: -0.0001

Data Index: 35644 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5510. Min Act: -0.0001

Data Index: 464022 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5662. Min Act: -0.0001

Data Index: 1273397 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5705. Min Act: -0.0001

Data Index: 410687 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5473. Min Act: -0.0001

Data Index: 902551 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5794. Min Act: -0.0001

Data Index: 304942 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5134. Min Act: -0.0001

Data Index: 49239 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5392. Min Act: -0.0001

Data Index: 526413 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5166. Min Act: -0.0001

Data Index: 753179 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5306. Min Act: -0.0001

Data Index: 675649 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5314. Min Act: -0.0001

Data Index: 450738 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5088. Min Act: -0.0001

Data Index: 431191 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5030. Min Act: -0.0001

Data Index: 1319436 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1072485 (C4 (Web Text))

Max Activating Token Index: 359