Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3312 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0598. Min Act: -0.0001

Data Index: 956759 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0598. Min Act: -0.0001

Data Index: 287064 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0557. Min Act: -0.0001

Data Index: 155705 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1216331 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1029806 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1337650 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0470. Min Act: -0.0001

Data Index: 701382 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0498. Min Act: -0.0001

Data Index: 950747 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0496. Min Act: -0.0001

Data Index: 50254 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0507. Min Act: -0.0001

Data Index: 791174 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1448129 (Python Code)

Max Activating Token Index: 652

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0489. Min Act: -0.0001

Data Index: 555617 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1421105 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1236832 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0486. Min Act: -0.0001

Data Index: 521475 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0458. Min Act: -0.0001

Data Index: 744054 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1234174 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0444. Min Act: -0.0001

Data Index: 495880 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1207329 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0521. Min Act: -0.0001

Data Index: 804497 (C4 (Web Text))

Max Activating Token Index: 519