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

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

Neuron 3481 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: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1316887 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1555409 (Python Code)

Max Activating Token Index: 462

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0477. Min Act: -0.0001

Data Index: 836064 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1507693 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1467216 (Python Code)

Max Activating Token Index: 659

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1554111 (Python Code)

Max Activating Token Index: 494

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0441. Min Act: -0.0001

Data Index: 665868 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1539806 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0430. Min Act: -0.0001

Data Index: 620270 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0435. Min Act: -0.0001

Data Index: 952735 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1474381 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1048522 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0424. Min Act: -0.0001

Data Index: 853380 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0426. Min Act: -0.0001

Data Index: 110726 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0430. Min Act: -0.0001

Data Index: 695016 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1423299 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1369040 (Python Code)

Max Activating Token Index: 897

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0422. Min Act: -0.0001

Data Index: 243123 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0424. Min Act: -0.0001

Data Index: 743038 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1549443 (Python Code)

Max Activating Token Index: 526