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

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

Neuron 2322 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: 2.2324. Min Range: -2.2324

Max Act: 2.1799. Min Act: -0.0000

Data Index: 43609 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 2.2324. Min Range: -2.2324

Max Act: 2.0661. Min Act: -0.0000

Data Index: 559213 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 2.2324. Min Range: -2.2324

Max Act: 2.2324. Min Act: -0.0000

Data Index: 70260 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.9559. Min Act: -0.0000

Data Index: 1135583 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.8390. Min Act: -0.0000

Data Index: 1020776 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.6025. Min Act: -0.0000

Data Index: 224621 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.7260. Min Act: -0.0000

Data Index: 585199 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1357336 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.6690. Min Act: -0.0000

Data Index: 655531 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.5721. Min Act: -0.0000

Data Index: 101617 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.4661. Min Act: -0.0000

Data Index: 1292299 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.6199. Min Act: -0.0000

Data Index: 1303143 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.5350. Min Act: -0.0000

Data Index: 425804 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.4999. Min Act: -0.0000

Data Index: 170169 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1005269 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.3824. Min Act: -0.0000

Data Index: 989010 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1103117 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.4524. Min Act: -0.0000

Data Index: 45079 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.4282. Min Act: -0.0000

Data Index: 929964 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 2.2324. Min Range: -2.2324

Max Act: 1.2978. Min Act: -0.0000

Data Index: 858373 (C4 (Web Text))

Max Activating Token Index: 970