Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 871 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2180. Min Act: -0.0001

Data Index: 1140884 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.3384. Min Act: -0.0001

Data Index: 456400 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2979. Min Act: -0.0001

Data Index: 745172 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2789. Min Act: -0.0001

Data Index: 797398 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2912. Min Act: -0.0001

Data Index: 1289955 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.1039. Min Act: -0.0001

Data Index: 983867 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.4997. Min Act: -0.0001

Data Index: 140872 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.8463. Min Act: -0.0001

Data Index: 1076480 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.6534. Min Act: -0.0001

Data Index: 603186 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.9336. Min Act: -0.0001

Data Index: 566079 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.7706. Min Act: -0.0001

Data Index: 824617 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.1433. Min Act: -0.0001

Data Index: 712556 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.5821. Min Act: -0.0001

Data Index: 1257476 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.4774. Min Act: -0.0001

Data Index: 1189415 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.1775. Min Act: -0.0001

Data Index: 179698 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.5223. Min Act: -0.0001

Data Index: 369683 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.5610. Min Act: -0.0001

Data Index: 7908 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.6824. Min Act: -0.0001

Data Index: 931852 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 3.4860. Min Range: -3.4860

Max Act: 2.4936. Min Act: -0.0001

Data Index: 679717 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.4860. Min Act: -0.0001

Data Index: 717224 (C4 (Web Text))

Max Activating Token Index: 238