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

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

Neuron 2935 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3881. Min Range: -1.3881

Max Act: 1.3881. Min Act: -0.0001

Data Index: 963204 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8308. Min Act: -0.0001

Data Index: 989939 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1060581 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8135. Min Act: -0.0001

Data Index: 1091777 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.8215. Min Act: -0.0001

Data Index: 997566 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6214. Min Act: -0.0001

Data Index: 1312274 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.7311. Min Act: -0.0001

Data Index: 731259 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.7092. Min Act: -0.0001

Data Index: 662247 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6535. Min Act: -0.0001

Data Index: 933702 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6950. Min Act: -0.0001

Data Index: 157404 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6817. Min Act: -0.0001

Data Index: 1810 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6577. Min Act: -0.0001

Data Index: 1050766 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6504. Min Act: -0.0001

Data Index: 1301418 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6734. Min Act: -0.0001

Data Index: 342890 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6898. Min Act: -0.0001

Data Index: 913442 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6850. Min Act: -0.0001

Data Index: 875298 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6444. Min Act: -0.0001

Data Index: 970860 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1019134 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6378. Min Act: -0.0001

Data Index: 539538 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 1.3881. Min Range: -1.3881

Max Act: 0.6407. Min Act: -0.0001

Data Index: 348837 (C4 (Web Text))

Max Activating Token Index: 580