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

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

Neuron 3186 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.2736. Min Act: -0.0001

Data Index: 323199 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.2414. Min Act: -0.0001

Data Index: 179915 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.1750. Min Act: -0.0001

Data Index: 1216956 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.1372. Min Act: -0.0001

Data Index: 1097909 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.1056. Min Act: -0.0001

Data Index: 1273188 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0821. Min Act: -0.0001

Data Index: 714271 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.1153. Min Act: -0.0001

Data Index: 369485 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0686. Min Act: -0.0001

Data Index: 335637 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0241. Min Act: -0.0001

Data Index: 1347179 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0904. Min Act: -0.0001

Data Index: 506440 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0817. Min Act: -0.0001

Data Index: 1316844 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0710. Min Act: -0.0001

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0816. Min Act: -0.0001

Data Index: 1336996 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0972. Min Act: -0.0001

Data Index: 808376 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.1020. Min Act: -0.0001

Data Index: 325250 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.2736. Min Range: -1.2736

Max Act: 0.9639. Min Act: -0.0001

Data Index: 477523 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0573. Min Act: -0.0001

Data Index: 589608 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0874. Min Act: -0.0001

Data Index: 566451 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0477. Min Act: -0.0001

Data Index: 830464 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.2736. Min Range: -1.2736

Max Act: 1.0460. Min Act: -0.0001

Data Index: 135083 (C4 (Web Text))

Max Activating Token Index: 431