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

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

Neuron 3150 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2153. Min Range: -4.2153

Max Act: 4.1012. Min Act: -0.0000

Data Index: 1303336 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 4.2153. Min Range: -4.2153

Max Act: 4.2153. Min Act: -0.0000

Data Index: 51645 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 4.2153. Min Range: -4.2153

Max Act: 4.1026. Min Act: -0.0000

Data Index: 114552 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.9261. Min Act: -0.0000

Data Index: 921583 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.7297. Min Act: -0.0000

Data Index: 877956 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.5921. Min Act: -0.0000

Data Index: 53876 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.6997. Min Act: -0.0000

Data Index: 1024872 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.7275. Min Act: -0.0000

Data Index: 767243 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.8730. Min Act: -0.0000

Data Index: 223256 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.6930. Min Act: -0.0000

Data Index: 721713 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.6792. Min Act: -0.0000

Data Index: 430942 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.6949. Min Act: -0.0000

Data Index: 288602 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.6644. Min Act: -0.0000

Data Index: 129053 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.6512. Min Act: -0.0000

Data Index: 886310 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.5942. Min Act: -0.0000

Data Index: 275700 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.5607. Min Act: -0.0000

Data Index: 779164 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.4076. Min Act: -0.0000

Data Index: 1032881 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.8415. Min Act: -0.0000

Data Index: 930605 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.6664. Min Act: -0.0000

Data Index: 509662 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 4.2153. Min Range: -4.2153

Max Act: 3.4989. Min Act: -0.0000

Data Index: 955039 (C4 (Web Text))

Max Activating Token Index: 836