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

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

Neuron 520 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3859. Min Range: -2.3859

Max Act: 2.3859. Min Act: -0.0000

Data Index: 1502613 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 2.3859. Min Range: -2.3859

Max Act: 2.1079. Min Act: -0.0000

Data Index: 1653674 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.9443. Min Act: -0.0000

Data Index: 1601169 (Python Code)

Max Activating Token Index: 480

Text #3

Max Range: 2.3859. Min Range: -2.3859

Max Act: 2.0038. Min Act: -0.0000

Data Index: 1417893 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.7988. Min Act: -0.0000

Data Index: 1583439 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.6947. Min Act: -0.0000

Data Index: 1594402 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1402578 (Python Code)

Max Activating Token Index: 265

Text #7

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.5941. Min Act: -0.0000

Data Index: 1460008 (Python Code)

Max Activating Token Index: 387

Text #8

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.5707. Min Act: -0.0000

Data Index: 1514678 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.5341. Min Act: -0.0000

Data Index: 1417123 (Python Code)

Max Activating Token Index: 352

Text #10

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1617860 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.3898. Min Act: -0.0000

Data Index: 1570906 (Python Code)

Max Activating Token Index: 317

Text #12

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.3738. Min Act: -0.0000

Data Index: 1493903 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1413348 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1556652 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1643104 (Python Code)

Max Activating Token Index: 895

Text #16

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1515072 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1589676 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1605075 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 2.3859. Min Range: -2.3859

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1361545 (Python Code)

Max Activating Token Index: 798