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

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

Neuron 424 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.3042. Min Act: -0.0000

Data Index: 680906 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.3107. Min Act: -0.0000

Data Index: 994479 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.3158. Min Act: -0.0000

Data Index: 796939 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2917. Min Act: -0.0000

Data Index: 465755 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1296050 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1344771 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.3013. Min Act: -0.0000

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2783. Min Act: -0.0000

Data Index: 418542 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1036308 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1017241 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2791. Min Act: -0.0000

Data Index: 598867 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1355963 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2636. Min Act: -0.0000

Data Index: 929885 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2751. Min Act: -0.0000

Data Index: 890499 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1272429 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2528. Min Act: -0.0000

Data Index: 998662 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2504. Min Act: -0.0000

Data Index: 412264 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2481. Min Act: -0.0000

Data Index: 130763 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2476. Min Act: -0.0000

Data Index: 929695 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2452. Min Act: -0.0000

Data Index: 718027 (C4 (Web Text))

Max Activating Token Index: 437