Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1992 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.9533. Min Act: -0.0000

Data Index: 246095 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.6191. Min Act: -0.0000

Data Index: 482376 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.2272. Min Act: -0.0000

Data Index: 374348 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.3126. Min Act: -0.0000

Data Index: 33320 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.2519. Min Act: 0.0000

Data Index: 226792 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.1732. Min Act: -0.0000

Data Index: 879000 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.1374. Min Act: -0.0000

Data Index: 279462 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.9941. Min Act: -0.0000

Data Index: 280925 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.0104. Min Act: -0.0000

Data Index: 964936 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.9533. Min Range: -1.9533

Max Act: 1.0237. Min Act: -0.0000

Data Index: 231859 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.9919. Min Act: 0.0000

Data Index: 885847 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.9993. Min Act: -0.0000

Data Index: 300030 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.9602. Min Act: -0.0000

Data Index: 882763 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.9053. Min Act: -0.0000

Data Index: 245163 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.8826. Min Act: -0.0000

Data Index: 965006 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.9304. Min Act: -0.0000

Data Index: 408172 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1214007 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.8176. Min Act: -0.0000

Data Index: 481951 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.8388. Min Act: 0.0000

Data Index: 367384 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.9533. Min Range: -1.9533

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1255244 (C4 (Web Text))

Max Activating Token Index: 97