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

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

Neuron 2244 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1152103 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1321106 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.6580. Min Act: -0.0000

Data Index: 724377 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1138334 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1154929 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5423. Min Act: -0.0000

Data Index: 218990 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5075. Min Act: -0.0000

Data Index: 821513 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5185. Min Act: -0.0000

Data Index: 922386 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5131. Min Act: -0.0000

Data Index: 150679 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1011688 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4970. Min Act: -0.0000

Data Index: 325134 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1126902 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4669. Min Act: -0.0000

Data Index: 478258 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4670. Min Act: -0.0000

Data Index: 392618 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1309390 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4630. Min Act: -0.0000

Data Index: 493033 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4576. Min Act: -0.0000

Data Index: 770136 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4734. Min Act: -0.0000

Data Index: 699533 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4845. Min Act: -0.0000

Data Index: 278216 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4661. Min Act: -0.0000

Data Index: 802785 (C4 (Web Text))

Max Activating Token Index: 407