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

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

Neuron 799 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.1292. Min Act: -0.0001

Data Index: 29350 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0867. Min Act: -0.0001

Data Index: 707250 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0083. Min Act: -0.0000

Data Index: 56769 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9509. Min Act: -0.0001

Data Index: 1233134 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9750. Min Act: -0.0001

Data Index: 749626 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1028109 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8638. Min Act: -0.0001

Data Index: 1160398 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9155. Min Act: -0.0001

Data Index: 685009 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8698. Min Act: -0.0001

Data Index: 787630 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9531. Min Act: -0.0001

Data Index: 1232099 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8607. Min Act: -0.0001

Data Index: 37851 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7127. Min Act: -0.0001

Data Index: 85706 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8338. Min Act: -0.0001

Data Index: 1204656 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1077795 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8491. Min Act: -0.0001

Data Index: 106487 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8383. Min Act: -0.0001

Data Index: 403761 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9193. Min Act: -0.0001

Data Index: 1267851 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8659. Min Act: -0.0001

Data Index: 653826 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8368. Min Act: -0.0001

Data Index: 1287158 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7830. Min Act: -0.0001

Data Index: 31757 (C4 (Web Text))

Max Activating Token Index: 818