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

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

Neuron 1610 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: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1411893 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0677. Min Act: -0.0001

Data Index: 492972 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1411649 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1493007 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1635929 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1651770 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1552555 (Python Code)

Max Activating Token Index: 279

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1563053 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1381296 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1592385 (Python Code)

Max Activating Token Index: 210

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0458. Min Act: -0.0001

Data Index: 46992 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1392793 (Python Code)

Max Activating Token Index: 371

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0460. Min Act: -0.0001

Data Index: 614303 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1465870 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0450. Min Act: -0.0001

Data Index: 635923 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1261176 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1535864 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1607491 (Python Code)

Max Activating Token Index: 746

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0446. Min Act: -0.0001

Data Index: 552050 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1408270 (Python Code)

Max Activating Token Index: 356