Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2548 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.9149. Min Act: -0.0001

Data Index: 1200640 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7989. Min Act: -0.0000

Data Index: 545681 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1374063 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7209. Min Act: -0.0001

Data Index: 940410 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7067. Min Act: -0.0000

Data Index: 236486 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6542. Min Act: -0.0000

Data Index: 971252 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6443. Min Act: -0.0000

Data Index: 468247 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6562. Min Act: -0.0000

Data Index: 351552 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6709. Min Act: -0.0000

Data Index: 36128 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6723. Min Act: -0.0001

Data Index: 913946 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6417. Min Act: -0.0000

Data Index: 20157 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6636. Min Act: -0.0000

Data Index: 951438 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6796. Min Act: -0.0001

Data Index: 408594 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6604. Min Act: -0.0001

Data Index: 1343410 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6094. Min Act: -0.0000

Data Index: 895141 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6473. Min Act: -0.0001

Data Index: 997581 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6438. Min Act: -0.0000

Data Index: 232414 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6009. Min Act: -0.0001

Data Index: 237585 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1330748 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6584. Min Act: -0.0001

Data Index: 459580 (C4 (Web Text))

Max Activating Token Index: 746