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

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

Neuron 2677 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1296574 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0511. Min Act: -0.0001

Data Index: 264235 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0505. Min Act: -0.0001

Data Index: 700577 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0498. Min Act: -0.0001

Data Index: 647225 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0492. Min Act: -0.0001

Data Index: 919695 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0486. Min Act: -0.0001

Data Index: 343005 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0474. Min Act: -0.0001

Data Index: 263853 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0467. Min Act: -0.0001

Data Index: 948360 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1068958 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0460. Min Act: -0.0001

Data Index: 450904 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1153926 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0442. Min Act: -0.0001

Data Index: 524527 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0446. Min Act: -0.0001

Data Index: 104911 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0445. Min Act: -0.0001

Data Index: 158465 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0449. Min Act: -0.0001

Data Index: 864591 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0440. Min Act: -0.0001

Data Index: 316933 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1001182 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0435. Min Act: -0.0001

Data Index: 3124 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1009035 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1050502 (C4 (Web Text))

Max Activating Token Index: 218