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

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

Neuron 1562 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0250. Min Range: -1.0250

Max Act: 1.0250. Min Act: -0.0001

Data Index: 828431 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.8181. Min Act: -0.0001

Data Index: 730694 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7315. Min Act: -0.0001

Data Index: 209798 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7518. Min Act: -0.0001

Data Index: 364148 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6874. Min Act: -0.0001

Data Index: 464093 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7008. Min Act: -0.0000

Data Index: 820641 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1341316 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6075. Min Act: -0.0001

Data Index: 1010853 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6313. Min Act: -0.0000

Data Index: 633012 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1238913 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1271744 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5999. Min Act: -0.0001

Data Index: 25962 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6307. Min Act: -0.0001

Data Index: 234648 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1276918 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5708. Min Act: -0.0000

Data Index: 917544 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1270586 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5608. Min Act: -0.0000

Data Index: 750186 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5726. Min Act: -0.0000

Data Index: 13027 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5728. Min Act: -0.0001

Data Index: 604226 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.5512. Min Act: -0.0001

Data Index: 457938 (C4 (Web Text))

Max Activating Token Index: 401