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

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

Neuron 4541 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1528577 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1428829 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7460. Min Act: -0.0000

Data Index: 230101 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1534393 (Python Code)

Max Activating Token Index: 645

Text #4

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1502784 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1551214 (Python Code)

Max Activating Token Index: 463

Text #6

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1498637 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1566990 (Python Code)

Max Activating Token Index: 968

Text #8

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1461178 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1394141 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1604844 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1531851 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1374491 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1409014 (Python Code)

Max Activating Token Index: 108

Text #14

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1531754 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1466088 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1365128 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1526662 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1457445 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1404613 (Python Code)

Max Activating Token Index: 341