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

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

Neuron 885 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7630. Min Act: -0.0000

Data Index: 200728 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6645. Min Act: -0.0000

Data Index: 190848 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7128. Min Act: -0.0000

Data Index: 787117 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6096. Min Act: -0.0000

Data Index: 1655837 (Python Code)

Max Activating Token Index: 257

Text #4

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1478665 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6727. Min Act: -0.0000

Data Index: 921374 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6756. Min Act: -0.0000

Data Index: 1330666 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5524. Min Act: -0.0001

Data Index: 1411543 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1415670 (Python Code)

Max Activating Token Index: 254

Text #9

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5531. Min Act: -0.0000

Data Index: 1554538 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1390855 (Python Code)

Max Activating Token Index: 526

Text #11

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6760. Min Act: -0.0000

Data Index: 497235 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6148. Min Act: -0.0000

Data Index: 1271257 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5583. Min Act: -0.0000

Data Index: 67405 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1574505 (Python Code)

Max Activating Token Index: 636

Text #15

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5788. Min Act: -0.0000

Data Index: 1441899 (Python Code)

Max Activating Token Index: 919

Text #16

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5225. Min Act: -0.0001

Data Index: 80987 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1617968 (Python Code)

Max Activating Token Index: 623

Text #18

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.5562. Min Act: -0.0000

Data Index: 534710 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1474193 (Python Code)

Max Activating Token Index: 815