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

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

Neuron 1535 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: 1.5353. Min Range: -1.5353

Max Act: 1.5353. Min Act: -0.0001

Data Index: 576522 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.3800. Min Act: -0.0001

Data Index: 488593 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.3054. Min Act: -0.0001

Data Index: 902697 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2358. Min Act: -0.0001

Data Index: 898919 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2745. Min Act: -0.0001

Data Index: 1023162 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2740. Min Act: -0.0001

Data Index: 1323146 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2698. Min Act: -0.0001

Data Index: 1167613 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.3081. Min Act: -0.0001

Data Index: 780607 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2154. Min Act: -0.0001

Data Index: 695258 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2100. Min Act: -0.0001

Data Index: 703905 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2381. Min Act: -0.0001

Data Index: 625676 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2368. Min Act: -0.0001

Data Index: 933422 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2560. Min Act: -0.0001

Data Index: 907149 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2118. Min Act: -0.0001

Data Index: 914391 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2008. Min Act: -0.0001

Data Index: 366375 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1967. Min Act: -0.0001

Data Index: 1322674 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1583. Min Act: -0.0001

Data Index: 91855 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1561. Min Act: -0.0001

Data Index: 1261125 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1783. Min Act: -0.0001

Data Index: 349156 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1066. Min Act: -0.0001

Data Index: 495718 (C4 (Web Text))

Max Activating Token Index: 51