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

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

Neuron 463 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.6188. Min Act: -0.0000

Data Index: 226467 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.9222. Min Act: -0.0000

Data Index: 745227 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.8018. Min Act: -0.0000

Data Index: 61824 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.9261. Min Act: -0.0000

Data Index: 711475 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.7072. Min Act: -0.0000

Data Index: 182394 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.7321. Min Act: -0.0000

Data Index: 1302086 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.5953. Min Act: -0.0000

Data Index: 244209 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.6796. Min Act: -0.0000

Data Index: 407660 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.5632. Min Act: -0.0000

Data Index: 591316 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.4761. Min Act: -0.0000

Data Index: 1405871 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.5597. Min Act: -0.0000

Data Index: 846312 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.6770. Min Act: -0.0000

Data Index: 913404 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.5239. Min Act: -0.0000

Data Index: 622717 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.4151. Min Act: -0.0000

Data Index: 948097 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.2484. Min Act: -0.0000

Data Index: 114754 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.3760. Min Act: -0.0000

Data Index: 1005858 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.3748. Min Act: -0.0000

Data Index: 906271 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.2370. Min Act: -0.0000

Data Index: 535450 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.3214. Min Act: -0.0000

Data Index: 1156910 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 3.6188. Min Range: -3.6188

Max Act: 2.4673. Min Act: -0.0000

Data Index: 1190222 (C4 (Web Text))

Max Activating Token Index: 845