Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3006 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5744. Min Act: -0.0000

Data Index: 11965 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5660. Min Act: -0.0000

Data Index: 258484 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4830. Min Act: -0.0000

Data Index: 671082 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1267501 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4673. Min Act: -0.0000

Data Index: 102251 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.3851. Min Act: 0.0000

Data Index: 42457 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.3276. Min Act: -0.0000

Data Index: 991300 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.3127. Min Act: -0.0000

Data Index: 835701 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.3034. Min Act: 0.0000

Data Index: 250363 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.3002. Min Act: -0.0000

Data Index: 821418 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1218368 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2961. Min Act: -0.0000

Data Index: 490915 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2944. Min Act: -0.0000

Data Index: 657 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2729. Min Act: -0.0000

Data Index: 34350 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2791. Min Act: -0.0000

Data Index: 985570 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2892. Min Act: -0.0000

Data Index: 670594 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2653. Min Act: -0.0000

Data Index: 557205 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1263958 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1102975 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.2661. Min Act: -0.0000

Data Index: 98332 (C4 (Web Text))

Max Activating Token Index: 382