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

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

Neuron 2641 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.3825. Min Act: -0.0001

Data Index: 6039 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2810. Min Act: -0.0001

Data Index: 1223541 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2693. Min Act: -0.0001

Data Index: 60118 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2917. Min Act: -0.0001

Data Index: 1042215 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.3848. Min Act: -0.0001

Data Index: 5528 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2523. Min Act: -0.0001

Data Index: 1105758 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.3247. Min Act: -0.0001

Data Index: 815127 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2801. Min Act: -0.0001

Data Index: 1284020 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.3391. Min Act: -0.0001

Data Index: 694668 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2496. Min Act: -0.0001

Data Index: 788031 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.1732. Min Act: -0.0001

Data Index: 594721 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2310. Min Act: -0.0001

Data Index: 3308 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2589. Min Act: -0.0001

Data Index: 801951 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2785. Min Act: -0.0001

Data Index: 912414 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2064. Min Act: -0.0001

Data Index: 1091193 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2299. Min Act: -0.0001

Data Index: 562764 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2238. Min Act: -0.0001

Data Index: 106981 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2544. Min Act: -0.0001

Data Index: 219561 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.2866. Min Act: -0.0001

Data Index: 650163 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.1502. Min Act: -0.0001

Data Index: 223134 (C4 (Web Text))

Max Activating Token Index: 567