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

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

Neuron 3601 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9641. Min Act: -0.0000

Data Index: 885414 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1262417 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7270. Min Act: -0.0000

Data Index: 809212 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6739. Min Act: -0.0000

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6844. Min Act: -0.0000

Data Index: 596390 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6817. Min Act: -0.0000

Data Index: 844278 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1222736 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6922. Min Act: -0.0000

Data Index: 206881 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5821. Min Act: -0.0000

Data Index: 802466 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6043. Min Act: -0.0000

Data Index: 988618 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6185. Min Act: -0.0000

Data Index: 594814 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5948. Min Act: -0.0000

Data Index: 592428 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5795. Min Act: -0.0000

Data Index: 448572 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5793. Min Act: -0.0000

Data Index: 394078 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5227. Min Act: -0.0000

Data Index: 719369 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5366. Min Act: -0.0000

Data Index: 390867 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5543. Min Act: -0.0000

Data Index: 443500 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1343252 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5995. Min Act: -0.0000

Data Index: 507050 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1258485 (C4 (Web Text))

Max Activating Token Index: 506