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

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

Neuron 131 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: 3.7857. Min Range: -3.7857

Max Act: 3.7857. Min Act: -0.0001

Data Index: 528112 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.1080. Min Act: -0.0001

Data Index: 261309 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.6590. Min Act: -0.0001

Data Index: 901993 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.2696. Min Act: -0.0001

Data Index: 348262 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.3698. Min Act: -0.0001

Data Index: 1206266 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.8832. Min Act: -0.0001

Data Index: 123632 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.7480. Min Act: -0.0001

Data Index: 789846 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.7345. Min Act: -0.0001

Data Index: 108948 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.9830. Min Act: -0.0001

Data Index: 484936 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.1959. Min Act: -0.0001

Data Index: 326779 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.0576. Min Act: -0.0001

Data Index: 823114 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.9957. Min Act: -0.0001

Data Index: 367711 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.8170. Min Act: -0.0001

Data Index: 385229 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.5128. Min Act: -0.0001

Data Index: 1045080 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.9536. Min Act: -0.0001

Data Index: 1281666 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.8114. Min Act: -0.0001

Data Index: 645727 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.8345. Min Act: -0.0001

Data Index: 315355 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.9395. Min Act: -0.0001

Data Index: 490533 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.9177. Min Act: -0.0001

Data Index: 64350 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.0541. Min Act: -0.0001

Data Index: 562402 (C4 (Web Text))

Max Activating Token Index: 83