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

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

Neuron 3649 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0000

Data Index: 580112 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0832. Min Act: -0.0000

Data Index: 780782 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0657. Min Act: -0.0000

Data Index: 643283 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0557. Min Act: -0.0000

Data Index: 390797 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1136385 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0528. Min Act: -0.0000

Data Index: 573662 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0532. Min Act: -0.0000

Data Index: 390555 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0521. Min Act: -0.0000

Data Index: 886338 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0552. Min Act: -0.0000

Data Index: 275582 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0498. Min Act: -0.0000

Data Index: 288692 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1252864 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0505. Min Act: -0.0000

Data Index: 734155 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0500. Min Act: -0.0000

Data Index: 448727 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0536. Min Act: -0.0000

Data Index: 511057 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0450. Min Act: -0.0000

Data Index: 201746 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0475. Min Act: -0.0000

Data Index: 773618 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0474. Min Act: -0.0000

Data Index: 722007 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0470. Min Act: -0.0000

Data Index: 207078 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0520. Min Act: -0.0000

Data Index: 811235 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0452. Min Act: -0.0000

Data Index: 868486 (C4 (Web Text))

Max Activating Token Index: 147