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

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

Neuron 3682 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.5530. Min Act: -0.0000

Data Index: 571699 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.4547. Min Act: -0.0001

Data Index: 133818 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.3993. Min Act: -0.0000

Data Index: 554822 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.3730. Min Act: -0.0001

Data Index: 1050745 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.2859. Min Act: -0.0001

Data Index: 664236 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.3108. Min Act: -0.0001

Data Index: 1307433 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.2557. Min Act: -0.0001

Data Index: 721042 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.2892. Min Act: -0.0000

Data Index: 529954 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.2473. Min Act: -0.0001

Data Index: 11831 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1412. Min Act: -0.0000

Data Index: 436157 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1465. Min Act: -0.0000

Data Index: 455184 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.2070. Min Act: -0.0000

Data Index: 600778 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1202923 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1507. Min Act: -0.0000

Data Index: 510467 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1515. Min Act: -0.0000

Data Index: 1030208 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1822. Min Act: -0.0001

Data Index: 1112577 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1762. Min Act: -0.0000

Data Index: 425917 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1364. Min Act: -0.0000

Data Index: 76564 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1276. Min Act: -0.0001

Data Index: 122188 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.5530. Min Range: -1.5530

Max Act: 1.1151. Min Act: -0.0001

Data Index: 508939 (C4 (Web Text))

Max Activating Token Index: 203