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

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

Neuron 4996 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.8952. Min Act: -0.0000

Data Index: 159166 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.6980. Min Act: -0.0000

Data Index: 718581 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.0165. Min Act: -0.0000

Data Index: 750304 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.2410. Min Act: -0.0000

Data Index: 608999 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.2816. Min Act: -0.0000

Data Index: 74621 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.1470. Min Act: -0.0000

Data Index: 189139 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.0098. Min Act: -0.0000

Data Index: 729859 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.2943. Min Act: -0.0000

Data Index: 702035 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.9551. Min Act: -0.0000

Data Index: 290527 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.9554. Min Act: -0.0000

Data Index: 527492 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.8753. Min Act: -0.0000

Data Index: 198610 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.7596. Min Act: -0.0000

Data Index: 1116807 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.6678. Min Act: -0.0000

Data Index: 1232295 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.5726. Min Act: -0.0000

Data Index: 35783 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.6477. Min Act: -0.0000

Data Index: 891496 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.8367. Min Act: -0.0000

Data Index: 345583 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.8007. Min Act: -0.0000

Data Index: 709371 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.6039. Min Act: -0.0000

Data Index: 699000 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.5936. Min Act: -0.0000

Data Index: 357252 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.5622. Min Act: -0.0000

Data Index: 743560 (C4 (Web Text))

Max Activating Token Index: 722