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

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

Neuron 1853 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.6492. Min Act: -0.0000

Data Index: 485088 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.5857. Min Act: -0.0000

Data Index: 680951 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1231496 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.5731. Min Act: -0.0000

Data Index: 996958 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.5125. Min Act: -0.0000

Data Index: 118471 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.4236. Min Act: -0.0000

Data Index: 279876 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.4794. Min Act: -0.0000

Data Index: 415884 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.4739. Min Act: -0.0000

Data Index: 353548 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1283331 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.4413. Min Act: -0.0000

Data Index: 305530 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3584. Min Act: -0.0000

Data Index: 288260 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1255600 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3074. Min Act: -0.0000

Data Index: 865454 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3520. Min Act: -0.0000

Data Index: 842401 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.4400. Min Act: -0.0000

Data Index: 260265 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1140154 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3239. Min Act: -0.0000

Data Index: 153030 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3248. Min Act: -0.0000

Data Index: 143306 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1263683 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 1.6655. Min Range: -1.6655

Max Act: 1.3298. Min Act: 0.0000

Data Index: 13797 (C4 (Web Text))

Max Activating Token Index: 78