Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 916 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.5976. Min Act: -0.0000

Data Index: 37994 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1277080 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1337875 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1017567 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1327568 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4321. Min Act: -0.0000

Data Index: 953797 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1144240 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1168268 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.3949. Min Act: -0.0000

Data Index: 818788 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4112. Min Act: -0.0000

Data Index: 102293 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4017. Min Act: -0.0000

Data Index: 688457 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4132. Min Act: -0.0000

Data Index: 222576 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4158. Min Act: -0.0000

Data Index: 186667 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1207566 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4056. Min Act: -0.0000

Data Index: 184868 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1162826 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.4177. Min Act: -0.0000

Data Index: 945008 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.3766. Min Act: -0.0000

Data Index: 125764 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.3848. Min Act: -0.0000

Data Index: 34239 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.5976. Min Range: -0.5976

Max Act: 0.3901. Min Act: -0.0000

Data Index: 672978 (C4 (Web Text))

Max Activating Token Index: 857