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

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

Neuron 2541 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.6712. Min Act: -0.0001

Data Index: 851361 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3831. Min Act: -0.0001

Data Index: 1336889 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4409. Min Act: -0.0001

Data Index: 905724 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.2890. Min Act: -0.0001

Data Index: 1261896 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3462. Min Act: -0.0001

Data Index: 463887 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3140. Min Act: -0.0001

Data Index: 1001073 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.1950. Min Act: -0.0001

Data Index: 945594 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.2274. Min Act: -0.0001

Data Index: 1048895 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.1245. Min Act: -0.0001

Data Index: 403706 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.0942. Min Act: -0.0001

Data Index: 660347 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.1569. Min Act: -0.0001

Data Index: 634072 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.0549. Min Act: -0.0001

Data Index: 321371 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.0358. Min Act: -0.0001

Data Index: 428208 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.0740. Min Act: -0.0001

Data Index: 514608 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.0263. Min Act: -0.0001

Data Index: 306038 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.6712. Min Range: -1.6712

Max Act: 0.9924. Min Act: -0.0001

Data Index: 274786 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.6712. Min Range: -1.6712

Max Act: 0.9041. Min Act: -0.0001

Data Index: 1241760 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.0039. Min Act: -0.0001

Data Index: 1190862 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.6712. Min Range: -1.6712

Max Act: 0.9434. Min Act: -0.0001

Data Index: 691164 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.6712. Min Range: -1.6712

Max Act: 0.9918. Min Act: -0.0001

Data Index: 1102814 (C4 (Web Text))

Max Activating Token Index: 305