Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0004

Data Index: 936495 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1730. Min Act: -0.0004

Data Index: 1015981 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1605. Min Act: -0.0004

Data Index: 279839 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1582. Min Act: -0.0004

Data Index: 773529 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1587. Min Act: -0.0004

Data Index: 269005 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1564. Min Act: -0.0004

Data Index: 259695 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1565. Min Act: -0.0004

Data Index: 599169 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1559. Min Act: -0.0004

Data Index: 971294 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1561. Min Act: -0.0004

Data Index: 343488 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1546. Min Act: -0.0004

Data Index: 371168 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1529. Min Act: -0.0004

Data Index: 1065803 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1501. Min Act: -0.0004

Data Index: 1290672 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1547. Min Act: -0.0004

Data Index: 655278 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1474. Min Act: -0.0004

Data Index: 689983 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1369. Min Act: -0.0004

Data Index: 660394 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1471. Min Act: -0.0004

Data Index: 217595 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1404. Min Act: -0.0004

Data Index: 840140 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1463. Min Act: -0.0004

Data Index: 141574 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1447. Min Act: -0.0004

Data Index: 639319 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1449. Min Act: -0.0004

Data Index: 1218571 (C4 (Web Text))

Max Activating Token Index: 24