Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1038291 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4306. Min Act: -0.0000

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4284. Min Act: -0.0000

Data Index: 833999 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4193. Min Act: -0.0000

Data Index: 101364 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4165. Min Act: -0.0000

Data Index: 814568 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3582. Min Act: -0.0000

Data Index: 626017 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3835. Min Act: -0.0000

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1286248 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3667. Min Act: -0.0000

Data Index: 387514 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4182. Min Act: -0.0000

Data Index: 647548 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3971. Min Act: -0.0001

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3738. Min Act: -0.0000

Data Index: 625333 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3431. Min Act: -0.0000

Data Index: 730285 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3468. Min Act: -0.0000

Data Index: 816274 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3599. Min Act: -0.0000

Data Index: 265596 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3764. Min Act: -0.0000

Data Index: 375558 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1321409 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3602. Min Act: -0.0000

Data Index: 427331 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3349. Min Act: -0.0000

Data Index: 765459 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3770. Min Act: -0.0000

Data Index: 171793 (C4 (Web Text))

Max Activating Token Index: 567