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

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

Neuron 3954 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.3080. Min Act: -0.0001

Data Index: 232673 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.3227. Min Act: -0.0001

Data Index: 66721 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2710. Min Act: -0.0001

Data Index: 665854 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2861. Min Act: -0.0001

Data Index: 1186763 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2777. Min Act: -0.0001

Data Index: 388219 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2844. Min Act: -0.0001

Data Index: 764053 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2554. Min Act: -0.0001

Data Index: 1296566 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2508. Min Act: -0.0001

Data Index: 6152 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2636. Min Act: -0.0001

Data Index: 306599 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2637. Min Act: -0.0001

Data Index: 47765 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2427. Min Act: -0.0001

Data Index: 66593 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2556. Min Act: -0.0001

Data Index: 186381 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2581. Min Act: -0.0001

Data Index: 2305 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2574. Min Act: -0.0001

Data Index: 765003 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2508. Min Act: -0.0001

Data Index: 497025 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2672. Min Act: -0.0001

Data Index: 304628 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2668. Min Act: -0.0001

Data Index: 737083 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1269793 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2548. Min Act: -0.0001

Data Index: 210610 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2519. Min Act: -0.0001

Data Index: 242911 (C4 (Web Text))

Max Activating Token Index: 629