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

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

Neuron 156 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.6131. Min Act: -0.0000

Data Index: 350617 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.4672. Min Act: -0.0000

Data Index: 60729 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.4226. Min Act: -0.0000

Data Index: 661516 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.4336. Min Act: -0.0000

Data Index: 365163 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.3950. Min Act: -0.0000

Data Index: 1343810 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1142735 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1133641 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.2824. Min Act: -0.0000

Data Index: 144458 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.2788. Min Act: -0.0000

Data Index: 399876 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1176237 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.2750. Min Act: -0.0000

Data Index: 411135 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.2999. Min Act: -0.0000

Data Index: 753009 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1169166 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1111312 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1959. Min Act: -0.0000

Data Index: 590562 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1581. Min Act: -0.0000

Data Index: 425644 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1109590 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1254263 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1761. Min Act: -0.0000

Data Index: 915041 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 1.6131. Min Range: -1.6131

Max Act: 1.1659. Min Act: -0.0000

Data Index: 617054 (C4 (Web Text))

Max Activating Token Index: 385