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

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

Neuron 313 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.5193. Min Act: -0.0002

Data Index: 473233 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.0252. Min Act: -0.0002

Data Index: 1260521 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.0857. Min Act: -0.0002

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.4087. Min Act: -0.0002

Data Index: 558376 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.1050. Min Act: -0.0002

Data Index: 608081 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.2509. Min Act: -0.0002

Data Index: 187480 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.2293. Min Act: -0.0002

Data Index: 204017 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.1186. Min Act: -0.0002

Data Index: 1297248 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.9453. Min Act: -0.0002

Data Index: 875584 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.0828. Min Act: -0.0002

Data Index: 243255 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.0963. Min Act: -0.0002

Data Index: 678001 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.1096. Min Act: -0.0002

Data Index: 517356 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.9555. Min Act: -0.0002

Data Index: 403891 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.9945. Min Act: -0.0002

Data Index: 151958 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.0351. Min Act: -0.0002

Data Index: 592256 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.8331. Min Act: -0.0002

Data Index: 999342 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.9454. Min Act: -0.0002

Data Index: 445843 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.9288. Min Act: -0.0002

Data Index: 91250 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.8918. Min Act: -0.0002

Data Index: 12732 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 3.5193. Min Range: -3.5193

Max Act: 1.7861. Min Act: -0.0002

Data Index: 348218 (C4 (Web Text))

Max Activating Token Index: 99