Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 663 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8421. Min Act: -0.0001

Data Index: 120423 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7568. Min Act: -0.0001

Data Index: 745561 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8268. Min Act: -0.0001

Data Index: 608751 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7617. Min Act: -0.0001

Data Index: 226150 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8295. Min Act: -0.0001

Data Index: 6293 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7478. Min Act: -0.0001

Data Index: 813345 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7738. Min Act: -0.0001

Data Index: 1257320 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7966. Min Act: -0.0001

Data Index: 877285 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8192. Min Act: -0.0001

Data Index: 1133965 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7074. Min Act: -0.0001

Data Index: 876809 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6685. Min Act: -0.0001

Data Index: 491866 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7283. Min Act: -0.0001

Data Index: 31196 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7063. Min Act: -0.0001

Data Index: 488802 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7418. Min Act: -0.0001

Data Index: 1086439 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7231. Min Act: -0.0001

Data Index: 1064854 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7354. Min Act: -0.0001

Data Index: 1015000 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7082. Min Act: -0.0001

Data Index: 192814 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7269. Min Act: -0.0001

Data Index: 768906 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6816. Min Act: -0.0001

Data Index: 684482 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6601. Min Act: -0.0001

Data Index: 487776 (C4 (Web Text))

Max Activating Token Index: 875