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

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

Neuron 3642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3712. Min Act: -0.0000

Data Index: 906233 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3450. Min Act: -0.0000

Data Index: 321910 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1210340 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3108. Min Act: -0.0001

Data Index: 585971 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3077. Min Act: -0.0001

Data Index: 898073 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1255847 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2993. Min Act: -0.0001

Data Index: 10237 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2608. Min Act: -0.0000

Data Index: 720957 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2555. Min Act: -0.0000

Data Index: 755332 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2529. Min Act: -0.0000

Data Index: 440627 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2618. Min Act: -0.0000

Data Index: 921299 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2709. Min Act: -0.0000

Data Index: 199353 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2457. Min Act: -0.0001

Data Index: 1199994 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2580. Min Act: -0.0001

Data Index: 1174345 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2480. Min Act: -0.0001

Data Index: 707166 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2468. Min Act: -0.0000

Data Index: 331801 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2336. Min Act: -0.0001

Data Index: 805765 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2452. Min Act: -0.0000

Data Index: 746558 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2458. Min Act: -0.0001

Data Index: 930367 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2419. Min Act: -0.0001

Data Index: 466424 (C4 (Web Text))

Max Activating Token Index: 979