Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3123 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1408088 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1560939 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1542806 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1523706 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1530092 (Python Code)

Max Activating Token Index: 436

Text #5

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1593749 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4991. Min Act: -0.0001

Data Index: 1558030 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1506506 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1362215 (Python Code)

Max Activating Token Index: 567

Text #9

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1570194 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1478124 (Python Code)

Max Activating Token Index: 337

Text #11

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1552447 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1603243 (Python Code)

Max Activating Token Index: 288

Text #13

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1624986 (Python Code)

Max Activating Token Index: 432

Text #14

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1595564 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1473556 (Python Code)

Max Activating Token Index: 755

Text #16

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1414281 (Python Code)

Max Activating Token Index: 411

Text #17

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1645869 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1392160 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 0.5493. Min Range: -0.5493

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1642008 (Python Code)

Max Activating Token Index: 391