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

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

Neuron 1801 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.3082. Min Act: -0.0001

Data Index: 998280 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1197999 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2607. Min Act: -0.0001

Data Index: 882021 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2609. Min Act: -0.0001

Data Index: 631107 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2570. Min Act: -0.0000

Data Index: 318336 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1212870 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2409. Min Act: -0.0001

Data Index: 176972 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2439. Min Act: -0.0000

Data Index: 914221 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2421. Min Act: -0.0001

Data Index: 53259 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2252. Min Act: -0.0001

Data Index: 262851 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1299816 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2179. Min Act: -0.0000

Data Index: 478422 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1358255 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2225. Min Act: -0.0001

Data Index: 740536 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2218. Min Act: -0.0000

Data Index: 441306 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1271812 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2080. Min Act: -0.0000

Data Index: 995317 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1246024 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2279. Min Act: -0.0000

Data Index: 287976 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1018076 (C4 (Web Text))

Max Activating Token Index: 1006