Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1485 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1939. Min Act: -0.0000

Data Index: 549745 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1927. Min Act: -0.0000

Data Index: 709277 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1138620 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1648. Min Act: -0.0000

Data Index: 509059 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1692. Min Act: -0.0000

Data Index: 408924 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1684. Min Act: -0.0000

Data Index: 506392 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1089427 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1610. Min Act: -0.0000

Data Index: 260969 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1585. Min Act: -0.0000

Data Index: 592881 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1272469 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1255615 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1671. Min Act: -0.0000

Data Index: 668605 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1595. Min Act: -0.0000

Data Index: 42535 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1651. Min Act: -0.0000

Data Index: 635372 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1284318 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1531. Min Act: -0.0000

Data Index: 14060 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1582. Min Act: -0.0000

Data Index: 383608 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1196541 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1510. Min Act: -0.0000

Data Index: 677891 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1457. Min Act: -0.0000

Data Index: 600531 (C4 (Web Text))

Max Activating Token Index: 584