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

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

Neuron 3256 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8808. Min Range: -2.8808

Max Act: 2.8808. Min Act: -0.0000

Data Index: 447683 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 2.8808. Min Range: -2.8808

Max Act: 2.7073. Min Act: -0.0001

Data Index: 678854 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 2.8808. Min Range: -2.8808

Max Act: 2.5205. Min Act: -0.0001

Data Index: 499900 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.8050. Min Act: -0.0000

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.8761. Min Act: -0.0001

Data Index: 672314 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1010223 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.7698. Min Act: -0.0000

Data Index: 318715 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.8403. Min Act: -0.0000

Data Index: 117642 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6469. Min Act: -0.0001

Data Index: 1202731 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6410. Min Act: -0.0000

Data Index: 1283086 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6546. Min Act: -0.0000

Data Index: 1284274 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1338188 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1053063 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.7227. Min Act: -0.0000

Data Index: 1054421 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6263. Min Act: -0.0000

Data Index: 157939 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6599. Min Act: -0.0000

Data Index: 798538 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1010923 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.6390. Min Act: -0.0000

Data Index: 166923 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 2.8808. Min Range: -2.8808

Max Act: 1.5627. Min Act: -0.0001

Data Index: 627627 (C4 (Web Text))

Max Activating Token Index: 76