Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 728 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9176. Min Range: -3.9176

Max Act: 3.9176. Min Act: -0.0000

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 3.9176. Min Range: -3.9176

Max Act: 3.1794. Min Act: -0.0000

Data Index: 1277628 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.4249. Min Act: -0.0000

Data Index: 1169057 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 3.9176. Min Range: -3.9176

Max Act: 3.1066. Min Act: -0.0000

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.6744. Min Act: -0.0000

Data Index: 646129 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.9238. Min Act: -0.0000

Data Index: 729164 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.5293. Min Act: -0.0000

Data Index: 393215 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.5174. Min Act: 0.0000

Data Index: 987966 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.5947. Min Act: -0.0000

Data Index: 596390 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.5687. Min Act: -0.0000

Data Index: 783965 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.2806. Min Act: -0.0000

Data Index: 953506 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.3801. Min Act: -0.0000

Data Index: 206881 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.4945. Min Act: -0.0000

Data Index: 1231005 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.3344. Min Act: -0.0000

Data Index: 1490480 (Python Code)

Max Activating Token Index: 225

Text #14

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.4330. Min Act: -0.0000

Data Index: 1321599 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.2756. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.3647. Min Act: -0.0000

Data Index: 23544 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.1240. Min Act: -0.0000

Data Index: 538634 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 3.9176. Min Range: -3.9176

Max Act: 2.0151. Min Act: 0.0000

Data Index: 448572 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 3.9176. Min Range: -3.9176

Max Act: 1.8070. Min Act: -0.0000

Data Index: 136662 (C4 (Web Text))

Max Activating Token Index: 814