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

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

Neuron 5510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5718. Min Act: -0.0001

Data Index: 540133 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5505. Min Act: -0.0001

Data Index: 779694 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4949. Min Act: -0.0001

Data Index: 9212 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4426. Min Act: -0.0001

Data Index: 566789 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4255. Min Act: -0.0001

Data Index: 4677 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4453. Min Act: -0.0001

Data Index: 1198797 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4487. Min Act: -0.0001

Data Index: 313297 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1300464 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3931. Min Act: -0.0001

Data Index: 403191 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4051. Min Act: -0.0001

Data Index: 300711 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4064. Min Act: -0.0001

Data Index: 1167919 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3999. Min Act: -0.0001

Data Index: 887096 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3982. Min Act: -0.0001

Data Index: 373366 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3703. Min Act: -0.0001

Data Index: 1015806 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3621. Min Act: -0.0001

Data Index: 1067381 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3577. Min Act: -0.0001

Data Index: 960110 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3592. Min Act: -0.0001

Data Index: 1314556 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3513. Min Act: -0.0001

Data Index: 16432 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3559. Min Act: -0.0001

Data Index: 950201 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3899. Min Act: -0.0001

Data Index: 825282 (C4 (Web Text))

Max Activating Token Index: 711