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

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

Neuron 3466 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: 4.9168. Min Range: -4.9168

Max Act: 4.9168. Min Act: -0.0000

Data Index: 573722 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 4.9168. Min Range: -4.9168

Max Act: 4.3226. Min Act: -0.0000

Data Index: 422198 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 4.9168. Min Range: -4.9168

Max Act: 4.4021. Min Act: -0.0000

Data Index: 988516 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 4.9168. Min Range: -4.9168

Max Act: 4.4283. Min Act: -0.0000

Data Index: 1013435 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 4.9168. Min Range: -4.9168

Max Act: 4.2464. Min Act: -0.0000

Data Index: 334579 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 4.9168. Min Range: -4.9168

Max Act: 4.2373. Min Act: -0.0000

Data Index: 878326 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 4.9168. Min Range: -4.9168

Max Act: 4.0197. Min Act: -0.0000

Data Index: 641895 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.9309. Min Act: -0.0000

Data Index: 343324 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.4624. Min Act: -0.0000

Data Index: 981879 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.5315. Min Act: -0.0000

Data Index: 151284 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.5333. Min Act: -0.0000

Data Index: 1081910 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.5314. Min Act: -0.0000

Data Index: 1072931 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.4909. Min Act: -0.0000

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.4972. Min Act: -0.0000

Data Index: 508590 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.4800. Min Act: -0.0000

Data Index: 1029541 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.3665. Min Act: -0.0000

Data Index: 290832 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.5708. Min Act: -0.0000

Data Index: 1105761 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.3997. Min Act: -0.0000

Data Index: 1009185 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.2483. Min Act: -0.0000

Data Index: 20053 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 4.9168. Min Range: -4.9168

Max Act: 2.3075. Min Act: -0.0000

Data Index: 93876 (C4 (Web Text))

Max Activating Token Index: 913