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

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

Neuron 5534 in Layer 1

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: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1040987 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1081935 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1035370 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1259287 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 295642 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 327976 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 119758 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1338053 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1054562 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 293484 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 466486 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 297954 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1403559 (Python Code)

Max Activating Token Index: 177

Text #13

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 790790 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 28628 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 12749 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0003

Data Index: 1354156 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 214165 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1212938 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0001. Min Range: -0.0001

Max Act: -0.0000. Min Act: -0.0002

Data Index: 210351 (C4 (Web Text))

Max Activating Token Index: 271