Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 92 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0006

Data Index: 590660 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0718. Min Act: -0.0006

Data Index: 192718 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0686. Min Act: -0.0006

Data Index: 1105804 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0709. Min Act: -0.0006

Data Index: 1282902 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0700. Min Act: -0.0006

Data Index: 935963 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0691. Min Act: -0.0006

Data Index: 794053 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0659. Min Act: -0.0006

Data Index: 1342682 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0663. Min Act: -0.0006

Data Index: 61308 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0660. Min Act: -0.0006

Data Index: 1089287 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0675. Min Act: -0.0006

Data Index: 281444 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0648. Min Act: -0.0006

Data Index: 279414 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0662. Min Act: -0.0006

Data Index: 849480 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0662. Min Act: -0.0006

Data Index: 947958 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0661. Min Act: -0.0006

Data Index: 118301 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0662. Min Act: -0.0006

Data Index: 697914 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0633. Min Act: -0.0006

Data Index: 948001 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0652. Min Act: -0.0006

Data Index: 806970 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0653. Min Act: -0.0006

Data Index: 266784 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0621. Min Act: -0.0006

Data Index: 202521 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0620. Min Act: -0.0006

Data Index: 188944 (C4 (Web Text))

Max Activating Token Index: 307