Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2762 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4259. Min Act: -0.0001

Data Index: 589553 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4030. Min Act: -0.0001

Data Index: 121921 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4007. Min Act: -0.0001

Data Index: 1316449 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1154820 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3869. Min Act: -0.0001

Data Index: 766738 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3954. Min Act: -0.0001

Data Index: 1272446 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3805. Min Act: -0.0000

Data Index: 490026 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3789. Min Act: -0.0001

Data Index: 815455 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3628. Min Act: -0.0001

Data Index: 193051 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3694. Min Act: -0.0001

Data Index: 73752 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3669. Min Act: -0.0001

Data Index: 1255454 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3486. Min Act: -0.0001

Data Index: 834611 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1009582 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3558. Min Act: -0.0001

Data Index: 513670 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1036002 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3438. Min Act: -0.0001

Data Index: 714342 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3627. Min Act: -0.0001

Data Index: 1189415 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3621. Min Act: -0.0001

Data Index: 822677 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3503. Min Act: -0.0001

Data Index: 810448 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3372. Min Act: -0.0001

Data Index: 794738 (C4 (Web Text))

Max Activating Token Index: 598