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

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

Neuron 5028 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.3890. Min Act: -0.0001

Data Index: 984380 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1900. Min Act: -0.0001

Data Index: 544692 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1428. Min Act: -0.0001

Data Index: 743876 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.2236. Min Act: -0.0001

Data Index: 211969 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1085. Min Act: -0.0001

Data Index: 910043 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0116. Min Act: -0.0001

Data Index: 582222 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0157. Min Act: -0.0001

Data Index: 973630 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9749. Min Act: -0.0001

Data Index: 1353819 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0068. Min Act: -0.0001

Data Index: 1181001 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9153. Min Act: -0.0001

Data Index: 1204310 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9925. Min Act: -0.0001

Data Index: 1080623 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9072. Min Act: -0.0001

Data Index: 600180 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9820. Min Act: -0.0001

Data Index: 1208235 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9230. Min Act: -0.0001

Data Index: 1336691 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9776. Min Act: -0.0001

Data Index: 386622 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1351646 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.8875. Min Act: -0.0001

Data Index: 294664 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9264. Min Act: -0.0001

Data Index: 1291799 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.8280. Min Act: -0.0001

Data Index: 669520 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9671. Min Act: -0.0001

Data Index: 749387 (C4 (Web Text))

Max Activating Token Index: 51