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

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

Neuron 3672 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: 0.4220. Min Range: -0.4220

Max Act: 0.4195. Min Act: -0.0001

Data Index: 165897 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.4220. Min Act: -0.0000

Data Index: 558099 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3933. Min Act: -0.0001

Data Index: 678446 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3843. Min Act: -0.0001

Data Index: 713457 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3960. Min Act: -0.0000

Data Index: 517943 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.4108. Min Act: -0.0001

Data Index: 1051356 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3762. Min Act: -0.0000

Data Index: 407273 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3872. Min Act: -0.0001

Data Index: 282733 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1245594 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3737. Min Act: -0.0001

Data Index: 61548 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3805. Min Act: -0.0001

Data Index: 588255 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1431141 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1188677 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1073108 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3483. Min Act: -0.0001

Data Index: 797810 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3586. Min Act: -0.0001

Data Index: 187555 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1197160 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1036516 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3616. Min Act: -0.0000

Data Index: 414597 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.4220. Min Range: -0.4220

Max Act: 0.3485. Min Act: -0.0000

Data Index: 878720 (C4 (Web Text))

Max Activating Token Index: 896