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

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

Neuron 4905 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: 2.8131. Min Range: -2.8131

Max Act: 2.8131. Min Act: -0.0000

Data Index: 1359216 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.2905. Min Act: -0.0000

Data Index: 1037567 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.0138. Min Act: -0.0000

Data Index: 935340 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.1412. Min Act: -0.0000

Data Index: 575845 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.2451. Min Act: -0.0000

Data Index: 855866 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.2732. Min Act: -0.0000

Data Index: 915219 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.1401. Min Act: -0.0000

Data Index: 601410 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.1225. Min Act: -0.0000

Data Index: 388339 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.0997. Min Act: -0.0000

Data Index: 380859 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.8231. Min Act: -0.0001

Data Index: 1151018 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.7734. Min Act: -0.0000

Data Index: 805457 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.9466. Min Act: -0.0000

Data Index: 14980 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.0444. Min Act: -0.0000

Data Index: 902477 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.7353. Min Act: -0.0000

Data Index: 143186 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.0409. Min Act: -0.0000

Data Index: 641157 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.8105. Min Act: -0.0000

Data Index: 504112 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.9066. Min Act: -0.0000

Data Index: 966533 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 2.8131. Min Range: -2.8131

Max Act: 2.0018. Min Act: -0.0000

Data Index: 1181782 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.7539. Min Act: -0.0000

Data Index: 843051 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 2.8131. Min Range: -2.8131

Max Act: 1.7443. Min Act: -0.0000

Data Index: 525502 (C4 (Web Text))

Max Activating Token Index: 352