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

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

Neuron 1148 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: 0.8708. Min Range: -0.8708

Max Act: 0.8708. Min Act: -0.0000

Data Index: 114780 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1200994 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.7402. Min Act: -0.0000

Data Index: 695865 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.7143. Min Act: -0.0000

Data Index: 426992 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.7139. Min Act: -0.0000

Data Index: 144128 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1229879 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6162. Min Act: -0.0000

Data Index: 332102 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5714. Min Act: -0.0000

Data Index: 425010 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5920. Min Act: -0.0001

Data Index: 73857 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1273809 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5888. Min Act: -0.0001

Data Index: 549096 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5489. Min Act: -0.0001

Data Index: 627113 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5258. Min Act: -0.0001

Data Index: 1092158 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1521361 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5728. Min Act: -0.0001

Data Index: 585622 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5548. Min Act: -0.0000

Data Index: 303353 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1149843 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5690. Min Act: -0.0000

Data Index: 354489 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5629. Min Act: -0.0001

Data Index: 1357940 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5561. Min Act: -0.0000

Data Index: 875364 (C4 (Web Text))

Max Activating Token Index: 146