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

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

Neuron 4701 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: 0.8682. Min Range: -0.8682

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1201688 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7780. Min Act: -0.0000

Data Index: 831010 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.8675. Min Act: -0.0000

Data Index: 244642 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.8040. Min Act: -0.0000

Data Index: 308130 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1037387 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7858. Min Act: -0.0000

Data Index: 433130 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7283. Min Act: -0.0000

Data Index: 923237 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7267. Min Act: -0.0000

Data Index: 888410 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1237515 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7105. Min Act: -0.0000

Data Index: 388859 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7018. Min Act: -0.0000

Data Index: 366469 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1332071 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6646. Min Act: -0.0000

Data Index: 994595 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1351400 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6682. Min Act: -0.0000

Data Index: 858469 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1246746 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6723. Min Act: -0.0000

Data Index: 486109 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1267233 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6718. Min Act: -0.0000

Data Index: 311137 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6074. Min Act: -0.0000

Data Index: 708158 (C4 (Web Text))

Max Activating Token Index: 994