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

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

Neuron 3329 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: 1.0442. Min Range: -1.0442

Max Act: 1.0076. Min Act: -0.0000

Data Index: 94206 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.0442. Min Range: -1.0442

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1082867 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1289391 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.0442. Min Range: -1.0442

Max Act: 1.0416. Min Act: -0.0000

Data Index: 421567 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 1.0442. Min Range: -1.0442

Max Act: 1.0036. Min Act: -0.0000

Data Index: 619479 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 1.0442. Min Range: -1.0442

Max Act: 1.0442. Min Act: -0.0000

Data Index: 801763 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9600. Min Act: -0.0000

Data Index: 869613 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1121600 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9473. Min Act: -0.0001

Data Index: 1003487 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.0442. Min Range: -1.0442

Max Act: 1.0280. Min Act: -0.0000

Data Index: 141369 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9622. Min Act: -0.0001

Data Index: 523381 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1041047 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1347194 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1121399 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.8260. Min Act: -0.0000

Data Index: 485361 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9304. Min Act: -0.0000

Data Index: 945824 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.8201. Min Act: -0.0000

Data Index: 258099 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1158115 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.9123. Min Act: -0.0000

Data Index: 153573 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1135562 (C4 (Web Text))

Max Activating Token Index: 928