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

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

Neuron 4948 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4425. Min Act: -0.0000

Data Index: 220940 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1159725 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3830. Min Act: -0.0000

Data Index: 264751 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4305. Min Act: -0.0000

Data Index: 556104 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3710. Min Act: -0.0000

Data Index: 39205 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1080416 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4147. Min Act: -0.0000

Data Index: 939557 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4131. Min Act: -0.0000

Data Index: 739921 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3846. Min Act: -0.0000

Data Index: 839438 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1045493 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3665. Min Act: -0.0000

Data Index: 763658 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1638550 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1012944 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4063. Min Act: -0.0000

Data Index: 204544 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3333. Min Act: -0.0000

Data Index: 875904 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3413. Min Act: -0.0000

Data Index: 82270 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3659. Min Act: -0.0000

Data Index: 864225 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3517. Min Act: -0.0000

Data Index: 535433 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3645. Min Act: -0.0000

Data Index: 354171 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3721. Min Act: -0.0000

Data Index: 59301 (C4 (Web Text))

Max Activating Token Index: 124