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

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

Neuron 3848 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6337. Min Act: -0.0002

Data Index: 977202 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6140. Min Act: -0.0002

Data Index: 152014 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6076. Min Act: -0.0002

Data Index: 963474 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5977. Min Act: -0.0002

Data Index: 642573 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5843. Min Act: -0.0002

Data Index: 920367 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5752. Min Act: -0.0002

Data Index: 741845 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5606. Min Act: -0.0002

Data Index: 1045219 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5484. Min Act: -0.0002

Data Index: 1263938 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5545. Min Act: -0.0002

Data Index: 771102 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5480. Min Act: -0.0002

Data Index: 1046701 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5485. Min Act: -0.0002

Data Index: 199917 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5443. Min Act: -0.0002

Data Index: 1346782 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5447. Min Act: -0.0002

Data Index: 1635 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5494. Min Act: -0.0002

Data Index: 813431 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5432. Min Act: -0.0002

Data Index: 142824 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5470. Min Act: -0.0002

Data Index: 1193160 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5394. Min Act: -0.0002

Data Index: 1187922 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5462. Min Act: -0.0002

Data Index: 126381 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5429. Min Act: -0.0002

Data Index: 1260349 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5365. Min Act: -0.0002

Data Index: 1021696 (C4 (Web Text))

Max Activating Token Index: 695