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

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

Neuron 3600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.6889. Min Act: -0.0001

Data Index: 1241072 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.6915. Min Act: -0.0000

Data Index: 573514 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5970. Min Act: -0.0000

Data Index: 336221 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5836. Min Act: -0.0001

Data Index: 993444 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5815. Min Act: -0.0001

Data Index: 826584 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5839. Min Act: -0.0000

Data Index: 514058 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1040037 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.5773. Min Act: -0.0000

Data Index: 942811 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4990. Min Act: -0.0001

Data Index: 699625 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4517. Min Act: -0.0001

Data Index: 481578 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3555. Min Act: -0.0001

Data Index: 1190659 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3347. Min Act: -0.0001

Data Index: 663307 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1197533 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4352. Min Act: -0.0001

Data Index: 973236 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1181934 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3206. Min Act: -0.0001

Data Index: 7633 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.2310. Min Act: -0.0001

Data Index: 1342850 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.4991. Min Act: -0.0001

Data Index: 601641 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.3603. Min Act: -0.0001

Data Index: 402811 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 1.6915. Min Range: -1.6915

Max Act: 1.2937. Min Act: -0.0000

Data Index: 686133 (C4 (Web Text))

Max Activating Token Index: 421