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

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

Neuron 2136 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: 1.3088. Min Range: -1.3088

Max Act: 1.3088. Min Act: -0.0001

Data Index: 494671 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2132. Min Act: -0.0001

Data Index: 553157 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9843. Min Act: -0.0000

Data Index: 387996 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9962. Min Act: -0.0001

Data Index: 848045 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9787. Min Act: 0.0000

Data Index: 1098311 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9069. Min Act: 0.0000

Data Index: 807961 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8686. Min Act: -0.0000

Data Index: 786537 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1273559 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9165. Min Act: -0.0000

Data Index: 31170 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8675. Min Act: -0.0001

Data Index: 96295 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8588. Min Act: -0.0000

Data Index: 908746 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1330596 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8219. Min Act: -0.0001

Data Index: 15655 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1003412 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.7918. Min Act: -0.0001

Data Index: 985072 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8004. Min Act: 0.0000

Data Index: 1346520 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.7947. Min Act: -0.0000

Data Index: 683712 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1004800 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1110460 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.7589. Min Act: -0.0001

Data Index: 694069 (C4 (Web Text))

Max Activating Token Index: 765