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

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

Neuron 5130 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5477. Min Act: -0.0000

Data Index: 916231 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5028. Min Act: -0.0000

Data Index: 517481 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5289. Min Act: -0.0000

Data Index: 720706 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1222915 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4663. Min Act: -0.0000

Data Index: 214371 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4784. Min Act: -0.0000

Data Index: 251502 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1344757 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4439. Min Act: -0.0000

Data Index: 84297 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4607. Min Act: -0.0000

Data Index: 559095 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4461. Min Act: -0.0000

Data Index: 925728 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4733. Min Act: -0.0000

Data Index: 878694 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1206632 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4564. Min Act: -0.0000

Data Index: 368520 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4846. Min Act: -0.0000

Data Index: 678540 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4669. Min Act: -0.0000

Data Index: 228931 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4138. Min Act: -0.0000

Data Index: 295222 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1135926 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4103. Min Act: -0.0000

Data Index: 143166 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4216. Min Act: -0.0000

Data Index: 717925 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4067. Min Act: -0.0000

Data Index: 70855 (C4 (Web Text))

Max Activating Token Index: 456