Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.3717. Min Act: -0.0000

Data Index: 1475758 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.5328. Min Act: -0.0000

Data Index: 1403442 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2806. Min Act: -0.0000

Data Index: 1577522 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.0825. Min Act: -0.0000

Data Index: 1374502 (Python Code)

Max Activating Token Index: 1000

Text #4

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2075. Min Act: -0.0000

Data Index: 1391814 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.0987. Min Act: -0.0000

Data Index: 1509400 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.0811. Min Act: -0.0000

Data Index: 1635403 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.0580. Min Act: -0.0000

Data Index: 1648547 (Python Code)

Max Activating Token Index: 244

Text #8

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8600. Min Act: -0.0000

Data Index: 1380805 (Python Code)

Max Activating Token Index: 1007

Text #9

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8673. Min Act: -0.0000

Data Index: 1616611 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8408. Min Act: -0.0000

Data Index: 1480238 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.9651. Min Act: -0.0000

Data Index: 1375884 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.9094. Min Act: -0.0000

Data Index: 1395529 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.0485. Min Act: -0.0000

Data Index: 1587488 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7620. Min Act: -0.0000

Data Index: 1510063 (Python Code)

Max Activating Token Index: 427

Text #15

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8425. Min Act: -0.0000

Data Index: 1627054 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.6798. Min Act: -0.0000

Data Index: 1564800 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7975. Min Act: -0.0000

Data Index: 1559142 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7791. Min Act: -0.0000

Data Index: 1635277 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.6489. Min Act: -0.0000

Data Index: 1487179 (Python Code)

Max Activating Token Index: 632