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

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

Neuron 238 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.5578. Min Act: -0.0000

Data Index: 1126279 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.6904. Min Act: -0.0000

Data Index: 1557388 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.9214. Min Act: -0.0000

Data Index: 1389539 (Python Code)

Max Activating Token Index: 1014

Text #3

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.8545. Min Act: -0.0000

Data Index: 982732 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.7058. Min Act: -0.0000

Data Index: 834412 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.6733. Min Act: -0.0000

Data Index: 612291 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.5128. Min Act: -0.0000

Data Index: 595746 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.6182. Min Act: -0.0000

Data Index: 416633 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.6656. Min Act: -0.0000

Data Index: 1491942 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.3013. Min Act: -0.0000

Data Index: 1180339 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.4957. Min Act: -0.0000

Data Index: 315591 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.3201. Min Act: -0.0000

Data Index: 72205 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.4474. Min Act: -0.0000

Data Index: 1288600 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.4819. Min Act: -0.0000

Data Index: 167022 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.3559. Min Act: -0.0000

Data Index: 1457328 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.6907. Min Act: -0.0000

Data Index: 1031790 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.3188. Min Act: -0.0000

Data Index: 895138 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.1990. Min Act: -0.0000

Data Index: 468902 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.3043. Min Act: -0.0000

Data Index: 889188 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 2.9214. Min Range: -2.9214

Max Act: 2.4133. Min Act: -0.0000

Data Index: 535197 (C4 (Web Text))

Max Activating Token Index: 1023