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

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

Neuron 1478 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2146. Min Act: -0.0001

Data Index: 278105 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2396. Min Act: -0.0001

Data Index: 145716 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2151. Min Act: -0.0000

Data Index: 438807 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2005. Min Act: -0.0000

Data Index: 664040 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2133. Min Act: -0.0001

Data Index: 832569 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1969. Min Act: -0.0001

Data Index: 123473 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1898. Min Act: -0.0001

Data Index: 342509 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1159620 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1904. Min Act: -0.0000

Data Index: 795792 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1731. Min Act: -0.0001

Data Index: 819260 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1922. Min Act: -0.0000

Data Index: 185177 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1934. Min Act: -0.0001

Data Index: 252438 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1872. Min Act: -0.0001

Data Index: 367870 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1284007 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1838. Min Act: -0.0001

Data Index: 821369 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1143633 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1688. Min Act: -0.0001

Data Index: 1071632 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1788. Min Act: -0.0001

Data Index: 42878 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1900. Min Act: -0.0001

Data Index: 10069 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1671. Min Act: -0.0001

Data Index: 385497 (C4 (Web Text))

Max Activating Token Index: 77