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

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

Neuron 2301 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7877. Min Act: -0.0000

Data Index: 435117 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1162890 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7138. Min Act: -0.0000

Data Index: 457049 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6977. Min Act: -0.0000

Data Index: 776371 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7207. Min Act: -0.0000

Data Index: 940464 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6786. Min Act: -0.0000

Data Index: 714045 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6144. Min Act: -0.0000

Data Index: 19001 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6131. Min Act: -0.0000

Data Index: 997573 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6438. Min Act: -0.0000

Data Index: 209678 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6407. Min Act: -0.0000

Data Index: 924175 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6337. Min Act: -0.0000

Data Index: 238798 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1109221 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6172. Min Act: -0.0000

Data Index: 371174 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5726. Min Act: -0.0000

Data Index: 192100 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1199246 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5626. Min Act: -0.0000

Data Index: 73373 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5499. Min Act: -0.0000

Data Index: 257150 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6053. Min Act: -0.0000

Data Index: 994702 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1148907 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5834. Min Act: -0.0000

Data Index: 235109 (C4 (Web Text))

Max Activating Token Index: 782