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

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

Neuron 3064 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: 0.1977. Min Range: -0.1977

Max Act: 0.1951. Min Act: -0.0001

Data Index: 885575 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1034029 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1739. Min Act: -0.0001

Data Index: 767113 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1586. Min Act: -0.0001

Data Index: 878938 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1716. Min Act: -0.0001

Data Index: 80990 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1850. Min Act: -0.0001

Data Index: 449594 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1708. Min Act: -0.0001

Data Index: 884126 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1470. Min Act: -0.0001

Data Index: 465256 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1337343 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1551. Min Act: -0.0001

Data Index: 666702 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1550. Min Act: -0.0001

Data Index: 718460 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1124066 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1324341 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1605. Min Act: -0.0001

Data Index: 860232 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1486. Min Act: -0.0001

Data Index: 512705 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1514. Min Act: -0.0001

Data Index: 636701 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1331275 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1415. Min Act: -0.0001

Data Index: 258047 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1124571 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1399. Min Act: -0.0001

Data Index: 143294 (C4 (Web Text))

Max Activating Token Index: 578