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

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

Neuron 512 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3821. Min Range: -5.3821

Max Act: 5.3821. Min Act: -0.0000

Data Index: 371362 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 5.3821. Min Range: -5.3821

Max Act: 5.3398. Min Act: -0.0000

Data Index: 1109599 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 5.3821. Min Range: -5.3821

Max Act: 5.2636. Min Act: -0.0000

Data Index: 26433 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.5473. Min Act: -0.0000

Data Index: 853996 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.0310. Min Act: -0.0000

Data Index: 545303 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.5233. Min Act: -0.0000

Data Index: 903486 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.7752. Min Act: -0.0000

Data Index: 1241043 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.5724. Min Act: -0.0000

Data Index: 1019245 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.4076. Min Act: -0.0000

Data Index: 1110510 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.3932. Min Act: -0.0000

Data Index: 284656 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 5.3821. Min Range: -5.3821

Max Act: 3.9752. Min Act: -0.0000

Data Index: 2577 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.0916. Min Act: -0.0000

Data Index: 1258491 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.1771. Min Act: -0.0000

Data Index: 141502 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.1258. Min Act: -0.0000

Data Index: 1116174 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 5.3821. Min Range: -5.3821

Max Act: 3.9567. Min Act: -0.0000

Data Index: 1252366 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 5.3821. Min Range: -5.3821

Max Act: 3.9273. Min Act: -0.0000

Data Index: 519635 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.2074. Min Act: -0.0000

Data Index: 1086827 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.0295. Min Act: -0.0000

Data Index: 496636 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.1591. Min Act: -0.0000

Data Index: 873976 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 5.3821. Min Range: -5.3821

Max Act: 4.3222. Min Act: -0.0000

Data Index: 708871 (C4 (Web Text))

Max Activating Token Index: 344