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

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

Neuron 2108 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0411. Min Range: -4.0411

Max Act: 4.0411. Min Act: -0.0000

Data Index: 1134165 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 4.0411. Min Range: -4.0411

Max Act: 3.3021. Min Act: -0.0000

Data Index: 539825 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 4.0411. Min Range: -4.0411

Max Act: 2.9641. Min Act: -0.0000

Data Index: 1302026 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 4.0411. Min Range: -4.0411

Max Act: 2.5370. Min Act: -0.0000

Data Index: 342765 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 4.0411. Min Range: -4.0411

Max Act: 2.7308. Min Act: -0.0000

Data Index: 723061 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 4.0411. Min Range: -4.0411

Max Act: 2.3267. Min Act: -0.0000

Data Index: 434636 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.8745. Min Act: -0.0000

Data Index: 108983 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 4.0411. Min Range: -4.0411

Max Act: 2.0599. Min Act: -0.0000

Data Index: 1054818 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.9278. Min Act: -0.0000

Data Index: 936629 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1051816 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.9586. Min Act: -0.0000

Data Index: 607524 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.7556. Min Act: -0.0000

Data Index: 1321517 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.9496. Min Act: -0.0000

Data Index: 86000 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.8550. Min Act: -0.0000

Data Index: 1018899 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.6381. Min Act: -0.0000

Data Index: 915519 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.7296. Min Act: -0.0000

Data Index: 1066991 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.7295. Min Act: -0.0000

Data Index: 849846 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.7058. Min Act: -0.0000

Data Index: 693328 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.4976. Min Act: -0.0000

Data Index: 1127470 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 4.0411. Min Range: -4.0411

Max Act: 1.5703. Min Act: -0.0000

Data Index: 300667 (C4 (Web Text))

Max Activating Token Index: 459