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

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

Neuron 4499 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: 0.4917. Min Range: -0.4917

Max Act: 0.4917. Min Act: -0.0000

Data Index: 254154 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3936. Min Act: -0.0000

Data Index: 41735 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3592. Min Act: -0.0000

Data Index: 125679 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3772. Min Act: -0.0000

Data Index: 893262 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1298677 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3363. Min Act: -0.0000

Data Index: 559726 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3238. Min Act: -0.0000

Data Index: 503122 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3187. Min Act: -0.0000

Data Index: 157462 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3297. Min Act: -0.0000

Data Index: 441439 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1200830 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3159. Min Act: -0.0000

Data Index: 881490 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3227. Min Act: -0.0000

Data Index: 912793 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3116. Min Act: 0.0000

Data Index: 1184178 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3009. Min Act: -0.0000

Data Index: 885074 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2848. Min Act: -0.0000

Data Index: 713710 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2819. Min Act: -0.0000

Data Index: 210223 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1006672 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1177827 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1071727 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1540621 (Python Code)

Max Activating Token Index: 481