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

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

Neuron 1318 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.7104. Min Act: -0.0001

Data Index: 468549 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6537. Min Act: -0.0001

Data Index: 1252162 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.7085. Min Act: -0.0001

Data Index: 823549 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6622. Min Act: -0.0001

Data Index: 748864 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6235. Min Act: -0.0001

Data Index: 688340 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6280. Min Act: -0.0001

Data Index: 129697 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5830. Min Act: -0.0001

Data Index: 233386 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6368. Min Act: -0.0001

Data Index: 916883 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5732. Min Act: -0.0001

Data Index: 1618 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6101. Min Act: -0.0001

Data Index: 1161338 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5722. Min Act: -0.0001

Data Index: 358728 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6338. Min Act: -0.0001

Data Index: 1127110 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5683. Min Act: -0.0001

Data Index: 1272033 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5320. Min Act: -0.0001

Data Index: 659712 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5578. Min Act: -0.0001

Data Index: 52434 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5641. Min Act: -0.0001

Data Index: 829352 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5810. Min Act: -0.0001

Data Index: 222973 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5797. Min Act: -0.0001

Data Index: 394408 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5917. Min Act: -0.0001

Data Index: 970669 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5381. Min Act: -0.0001

Data Index: 1091599 (C4 (Web Text))

Max Activating Token Index: 195