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

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

Neuron 2900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.3102. Min Act: -0.0000

Data Index: 530277 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2941. Min Act: -0.0001

Data Index: 648863 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2991. Min Act: -0.0000

Data Index: 216989 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2966. Min Act: -0.0000

Data Index: 621765 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2621. Min Act: -0.0001

Data Index: 1029980 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2938. Min Act: -0.0000

Data Index: 720712 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1322754 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2770. Min Act: -0.0001

Data Index: 205412 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1154307 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2443. Min Act: -0.0000

Data Index: 907215 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1111796 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2274. Min Act: -0.0000

Data Index: 345823 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1071212 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2190. Min Act: -0.0000

Data Index: 485956 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2493. Min Act: -0.0000

Data Index: 956558 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2400. Min Act: -0.0000

Data Index: 526275 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2145. Min Act: -0.0000

Data Index: 236183 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1323602 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1290959 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2345. Min Act: -0.0001

Data Index: 325792 (C4 (Web Text))

Max Activating Token Index: 100