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

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

Neuron 3145 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0137. Min Act: -0.0000

Data Index: 763414 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2508. Min Act: -0.0000

Data Index: 966177 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0953. Min Act: -0.0000

Data Index: 184925 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1204639 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0467. Min Act: -0.0000

Data Index: 136954 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1013442 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0611. Min Act: -0.0000

Data Index: 648166 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0560. Min Act: -0.0000

Data Index: 552559 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0467. Min Act: -0.0000

Data Index: 639835 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0476. Min Act: -0.0000

Data Index: 89009 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1300229 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0394. Min Act: -0.0000

Data Index: 87925 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0442. Min Act: -0.0000

Data Index: 75510 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1318919 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0428. Min Act: -0.0000

Data Index: 609113 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1240235 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1390877 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0375. Min Act: -0.0000

Data Index: 98499 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0445. Min Act: -0.0000

Data Index: 263626 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.0434. Min Act: -0.0000

Data Index: 270273 (C4 (Web Text))

Max Activating Token Index: 732