Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 197 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.7474. Min Act: -0.0001

Data Index: 1185302 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.6336. Min Act: -0.0001

Data Index: 711209 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5929. Min Act: -0.0001

Data Index: 1294177 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5104. Min Act: -0.0001

Data Index: 967977 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5480. Min Act: -0.0001

Data Index: 540848 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5466. Min Act: -0.0001

Data Index: 697252 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5585. Min Act: -0.0001

Data Index: 2432 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5394. Min Act: -0.0001

Data Index: 896867 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5390. Min Act: -0.0001

Data Index: 840481 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5324. Min Act: -0.0001

Data Index: 97990 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5306. Min Act: -0.0001

Data Index: 26569 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5380. Min Act: -0.0001

Data Index: 281488 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5336. Min Act: -0.0001

Data Index: 484187 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5350. Min Act: -0.0001

Data Index: 658301 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5348. Min Act: -0.0001

Data Index: 1307058 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5044. Min Act: -0.0001

Data Index: 1301023 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5485. Min Act: -0.0001

Data Index: 249628 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.4895. Min Act: -0.0001

Data Index: 1348642 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5059. Min Act: -0.0001

Data Index: 255622 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.7474. Min Range: -0.7474

Max Act: 0.5026. Min Act: -0.0001

Data Index: 645842 (C4 (Web Text))

Max Activating Token Index: 32