Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 47 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3411. Min Act: -0.0001

Data Index: 968175 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2630. Min Act: -0.0001

Data Index: 32562 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2702. Min Act: -0.0001

Data Index: 423299 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.1335. Min Act: -0.0001

Data Index: 612420 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.1009. Min Act: -0.0001

Data Index: 1264870 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.1233. Min Act: -0.0001

Data Index: 280725 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0933. Min Act: -0.0001

Data Index: 1201436 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0851. Min Act: -0.0001

Data Index: 1307115 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.9933. Min Act: -0.0001

Data Index: 982463 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2009. Min Act: -0.0001

Data Index: 590116 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.1253. Min Act: -0.0001

Data Index: 839787 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0645. Min Act: -0.0001

Data Index: 658079 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0422. Min Act: -0.0001

Data Index: 686682 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0267. Min Act: -0.0001

Data Index: 788201 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0560. Min Act: -0.0001

Data Index: 1262157 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0009. Min Act: -0.0001

Data Index: 895518 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0091. Min Act: -0.0001

Data Index: 995241 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.0658. Min Act: -0.0001

Data Index: 816487 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.9712. Min Act: -0.0001

Data Index: 789775 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.9666. Min Act: -0.0001

Data Index: 41903 (C4 (Web Text))

Max Activating Token Index: 41