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

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

Neuron 1219 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0815. Min Range: -5.0815

Max Act: 5.0815. Min Act: -0.0000

Data Index: 70833 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 5.0815. Min Range: -5.0815

Max Act: 4.3238. Min Act: -0.0000

Data Index: 703637 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 5.0815. Min Range: -5.0815

Max Act: 4.3831. Min Act: -0.0000

Data Index: 780823 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 5.0815. Min Range: -5.0815

Max Act: 4.1977. Min Act: -0.0000

Data Index: 1246944 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 5.0815. Min Range: -5.0815

Max Act: 3.8528. Min Act: -0.0000

Data Index: 464096 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 5.0815. Min Range: -5.0815

Max Act: 3.9578. Min Act: -0.0000

Data Index: 124702 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 5.0815. Min Range: -5.0815

Max Act: 3.6460. Min Act: -0.0000

Data Index: 210965 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 5.0815. Min Range: -5.0815

Max Act: 3.6616. Min Act: -0.0000

Data Index: 173923 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 5.0815. Min Range: -5.0815

Max Act: 3.4221. Min Act: -0.0000

Data Index: 13406 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 5.0815. Min Range: -5.0815

Max Act: 3.0935. Min Act: -0.0000

Data Index: 538187 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 5.0815. Min Range: -5.0815

Max Act: 2.9950. Min Act: -0.0000

Data Index: 1184867 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 5.0815. Min Range: -5.0815

Max Act: 2.7366. Min Act: -0.0000

Data Index: 127572 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 5.0815. Min Range: -5.0815

Max Act: 2.6533. Min Act: -0.0000

Data Index: 907733 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 5.0815. Min Range: -5.0815

Max Act: 2.6557. Min Act: -0.0000

Data Index: 565666 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 5.0815. Min Range: -5.0815

Max Act: 2.5027. Min Act: -0.0000

Data Index: 101546 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 5.0815. Min Range: -5.0815

Max Act: 2.4453. Min Act: -0.0000

Data Index: 506338 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 5.0815. Min Range: -5.0815

Max Act: 2.1297. Min Act: -0.0000

Data Index: 550966 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 5.0815. Min Range: -5.0815

Max Act: 1.5185. Min Act: -0.0000

Data Index: 146862 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 5.0815. Min Range: -5.0815

Max Act: 1.5794. Min Act: -0.0000

Data Index: 586677 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 5.0815. Min Range: -5.0815

Max Act: 1.4797. Min Act: -0.0000

Data Index: 550016 (C4 (Web Text))

Max Activating Token Index: 134