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

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

Neuron 3435 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0550. Min Range: -3.0550

Max Act: 3.0550. Min Act: -0.0001

Data Index: 203256 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 3.0550. Min Range: -3.0550

Max Act: 2.4362. Min Act: -0.0001

Data Index: 392625 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 3.0550. Min Range: -3.0550

Max Act: 2.3665. Min Act: -0.0001

Data Index: 1190632 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.0550. Min Range: -3.0550

Max Act: 2.1594. Min Act: -0.0001

Data Index: 260062 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.8572. Min Act: -0.0001

Data Index: 752550 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.9410. Min Act: -0.0001

Data Index: 275157 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 3.0550. Min Range: -3.0550

Max Act: 2.1446. Min Act: -0.0001

Data Index: 781775 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.4707. Min Act: -0.0001

Data Index: 957309 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.7642. Min Act: -0.0001

Data Index: 604680 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 3.0550. Min Range: -3.0550

Max Act: 2.1800. Min Act: -0.0001

Data Index: 786162 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.8136. Min Act: -0.0001

Data Index: 42436 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.7975. Min Act: -0.0001

Data Index: 358948 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.6385. Min Act: -0.0001

Data Index: 121509 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.6174. Min Act: -0.0001

Data Index: 987229 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.6100. Min Act: -0.0001

Data Index: 785495 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.6395. Min Act: -0.0001

Data Index: 153423 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.4304. Min Act: -0.0001

Data Index: 783172 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.6975. Min Act: -0.0001

Data Index: 1335623 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.4421. Min Act: -0.0001

Data Index: 545352 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 3.0550. Min Range: -3.0550

Max Act: 1.1886. Min Act: -0.0001

Data Index: 1132084 (C4 (Web Text))

Max Activating Token Index: 100