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

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

Neuron 1227 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1946. Min Act: -0.0001

Data Index: 1074384 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1740. Min Act: -0.0001

Data Index: 806185 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1968. Min Act: -0.0001

Data Index: 556041 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1758. Min Act: -0.0001

Data Index: 488915 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1775. Min Act: -0.0001

Data Index: 841127 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1761. Min Act: -0.0001

Data Index: 493395 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1499. Min Act: -0.0001

Data Index: 860200 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1643. Min Act: -0.0001

Data Index: 928066 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1550. Min Act: -0.0001

Data Index: 912006 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1671. Min Act: -0.0001

Data Index: 703171 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1605. Min Act: -0.0001

Data Index: 27180 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1540. Min Act: -0.0001

Data Index: 282803 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1591. Min Act: -0.0001

Data Index: 416377 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1570. Min Act: -0.0001

Data Index: 956744 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1583. Min Act: -0.0001

Data Index: 387648 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1632. Min Act: -0.0001

Data Index: 473725 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1554. Min Act: -0.0001

Data Index: 97242 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1559. Min Act: -0.0001

Data Index: 408095 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1527. Min Act: -0.0001

Data Index: 132530 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1534. Min Act: -0.0001

Data Index: 885578 (C4 (Web Text))

Max Activating Token Index: 549