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

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

Neuron 864 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: 1.1586. Min Range: -1.1586

Max Act: 1.1586. Min Act: -0.0000

Data Index: 1290282 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0300. Min Act: -0.0001

Data Index: 539207 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1099463 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9339. Min Act: -0.0000

Data Index: 228598 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9473. Min Act: -0.0001

Data Index: 604162 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9571. Min Act: -0.0000

Data Index: 837798 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9479. Min Act: -0.0001

Data Index: 997864 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8616. Min Act: -0.0001

Data Index: 689608 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1213094 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8348. Min Act: -0.0001

Data Index: 819471 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8514. Min Act: -0.0000

Data Index: 497762 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8428. Min Act: -0.0001

Data Index: 638849 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1343651 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8326. Min Act: -0.0001

Data Index: 219151 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8457. Min Act: -0.0000

Data Index: 417205 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1269181 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8087. Min Act: -0.0000

Data Index: 389763 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8173. Min Act: -0.0000

Data Index: 943050 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8671. Min Act: -0.0001

Data Index: 1298447 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1121380 (C4 (Web Text))

Max Activating Token Index: 24