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

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

Neuron 2125 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: 2.5612. Min Range: -2.5612

Max Act: 2.5612. Min Act: -0.0000

Data Index: 1316453 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 2.5612. Min Range: -2.5612

Max Act: 2.0172. Min Act: -0.0000

Data Index: 1014750 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.8944. Min Act: -0.0000

Data Index: 837995 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.7352. Min Act: -0.0000

Data Index: 883074 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.9906. Min Act: -0.0000

Data Index: 1192058 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.4280. Min Act: -0.0000

Data Index: 1207783 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.6691. Min Act: -0.0000

Data Index: 208873 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.9611. Min Act: -0.0000

Data Index: 1197399 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1243230 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.8124. Min Act: -0.0000

Data Index: 1359608 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.8234. Min Act: -0.0000

Data Index: 508166 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.5240. Min Act: -0.0000

Data Index: 218121 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.7918. Min Act: -0.0000

Data Index: 224392 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.6770. Min Act: -0.0000

Data Index: 1236225 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.6530. Min Act: -0.0000

Data Index: 368543 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.6157. Min Act: -0.0000

Data Index: 462426 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.5747. Min Act: -0.0000

Data Index: 1256964 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1364274 (Python Code)

Max Activating Token Index: 558

Text #18

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.4938. Min Act: -0.0000

Data Index: 380455 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 2.5612. Min Range: -2.5612

Max Act: 1.7446. Min Act: -0.0000

Data Index: 463191 (C4 (Web Text))

Max Activating Token Index: 287