Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 925 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.7537. Min Act: -0.0001

Data Index: 784222 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1316070 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6226. Min Act: -0.0001

Data Index: 1026135 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6197. Min Act: -0.0001

Data Index: 366461 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6059. Min Act: -0.0001

Data Index: 38836 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5744. Min Act: -0.0001

Data Index: 180044 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5545. Min Act: -0.0001

Data Index: 917149 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5702. Min Act: -0.0000

Data Index: 272037 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5848. Min Act: -0.0001

Data Index: 181391 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5163. Min Act: -0.0001

Data Index: 115857 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5052. Min Act: -0.0000

Data Index: 372325 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5157. Min Act: -0.0001

Data Index: 17233 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1177708 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5403. Min Act: -0.0000

Data Index: 649454 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5236. Min Act: -0.0001

Data Index: 822302 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5049. Min Act: -0.0000

Data Index: 377747 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5011. Min Act: -0.0001

Data Index: 41246 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5192. Min Act: -0.0001

Data Index: 827338 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5108. Min Act: -0.0001

Data Index: 432327 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1124194 (C4 (Web Text))

Max Activating Token Index: 616