Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.1756. Min Range: -5.1756

Max Act: 5.1756. Min Act: -0.0001

Data Index: 223209 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.8396. Min Act: -0.0000

Data Index: 1239308 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 5.1756. Min Range: -5.1756

Max Act: 5.0028. Min Act: -0.0001

Data Index: 1140303 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.6080. Min Act: -0.0000

Data Index: 176690 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.6911. Min Act: -0.0000

Data Index: 1222631 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 5.1756. Min Range: -5.1756

Max Act: 3.8897. Min Act: -0.0001

Data Index: 1278115 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.3606. Min Act: -0.0000

Data Index: 237727 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 5.1756. Min Range: -5.1756

Max Act: 5.0174. Min Act: -0.0000

Data Index: 431834 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.4914. Min Act: -0.0000

Data Index: 1210622 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.4670. Min Act: -0.0001

Data Index: 536665 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.6082. Min Act: -0.0000

Data Index: 600890 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.4478. Min Act: -0.0001

Data Index: 1722152 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.1406. Min Act: -0.0001

Data Index: 1019979 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.2289. Min Act: -0.0000

Data Index: 1824909 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.0993. Min Act: -0.0001

Data Index: 892229 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.3339. Min Act: -0.0000

Data Index: 545237 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.0380. Min Act: -0.0000

Data Index: 1421474 (The Pile)

Max Activating Token Index: 26

Text #17

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.3261. Min Act: -0.0000

Data Index: 345609 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.4315. Min Act: -0.0001

Data Index: 775254 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 5.1756. Min Range: -5.1756

Max Act: 4.2483. Min Act: -0.0001

Data Index: 1115680 (The Pile)

Max Activating Token Index: 79