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

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

Neuron 1259 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0798. Min Range: -1.0798

Max Act: 1.0798. Min Act: -0.0000

Data Index: 264561 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1010812 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9931. Min Act: -0.0000

Data Index: 812703 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9205. Min Act: -0.0000

Data Index: 907997 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.0798. Min Range: -1.0798

Max Act: 1.0074. Min Act: -0.0000

Data Index: 896089 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8862. Min Act: -0.0000

Data Index: 969442 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9030. Min Act: -0.0000

Data Index: 921222 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8301. Min Act: -0.0000

Data Index: 887394 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8517. Min Act: -0.0000

Data Index: 367979 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7364. Min Act: -0.0000

Data Index: 885594 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8014. Min Act: -0.0000

Data Index: 196844 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1000931 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1326907 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7637. Min Act: -0.0000

Data Index: 767392 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7472. Min Act: -0.0000

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7312. Min Act: -0.0000

Data Index: 229158 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1013948 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1184692 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1535771 (Python Code)

Max Activating Token Index: 476