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

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

Neuron 4705 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7431. Min Range: -6.7431

Max Act: 6.7431. Min Act: -0.0001

Data Index: 592782 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 6.7431. Min Range: -6.7431

Max Act: 5.7203. Min Act: -0.0001

Data Index: 725420 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 6.7431. Min Range: -6.7431

Max Act: 5.3116. Min Act: -0.0001

Data Index: 1214589 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 6.7431. Min Range: -6.7431

Max Act: 5.3487. Min Act: -0.0001

Data Index: 1321530 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 6.7431. Min Range: -6.7431

Max Act: 5.0823. Min Act: -0.0000

Data Index: 1060340 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.7036. Min Act: -0.0001

Data Index: 444364 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 6.7431. Min Range: -6.7431

Max Act: 3.9087. Min Act: -0.0001

Data Index: 760653 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.5722. Min Act: -0.0001

Data Index: 917010 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.4018. Min Act: -0.0001

Data Index: 741607 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.1839. Min Act: -0.0001

Data Index: 1146638 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.3066. Min Act: -0.0000

Data Index: 335446 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.2343. Min Act: -0.0000

Data Index: 385985 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.3897. Min Act: -0.0001

Data Index: 273198 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 6.7431. Min Range: -6.7431

Max Act: 3.9909. Min Act: -0.0000

Data Index: 1009750 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.0653. Min Act: -0.0001

Data Index: 11374 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.0419. Min Act: -0.0000

Data Index: 1321332 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.0354. Min Act: -0.0000

Data Index: 1032948 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 6.7431. Min Range: -6.7431

Max Act: 4.1862. Min Act: -0.0000

Data Index: 1333495 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 6.7431. Min Range: -6.7431

Max Act: 3.9841. Min Act: -0.0001

Data Index: 166355 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 6.7431. Min Range: -6.7431

Max Act: 3.5140. Min Act: -0.0001

Data Index: 939546 (C4 (Web Text))

Max Activating Token Index: 971