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

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

Neuron 5282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3651. Min Act: -0.0001

Data Index: 972498 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1332052 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3561. Min Act: -0.0001

Data Index: 504581 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3210. Min Act: -0.0001

Data Index: 93634 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3095. Min Act: -0.0001

Data Index: 10083 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3216. Min Act: -0.0001

Data Index: 691042 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3023. Min Act: -0.0001

Data Index: 1112391 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3196. Min Act: -0.0001

Data Index: 13250 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3274. Min Act: -0.0001

Data Index: 89129 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1340005 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2985. Min Act: -0.0001

Data Index: 80510 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2963. Min Act: -0.0001

Data Index: 987183 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3075. Min Act: -0.0001

Data Index: 234548 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2785. Min Act: -0.0001

Data Index: 558090 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3216. Min Act: -0.0001

Data Index: 602438 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2920. Min Act: -0.0001

Data Index: 953941 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2810. Min Act: -0.0001

Data Index: 749406 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2785. Min Act: -0.0001

Data Index: 469147 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2820. Min Act: -0.0001

Data Index: 201967 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3056. Min Act: -0.0001

Data Index: 88906 (C4 (Web Text))

Max Activating Token Index: 655