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

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

Neuron 312 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3514. Min Act: -0.0005

Data Index: 398868 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3089. Min Act: -0.0005

Data Index: 480309 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3194. Min Act: -0.0005

Data Index: 979625 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3050. Min Act: -0.0005

Data Index: 1290501 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3074. Min Act: -0.0005

Data Index: 325783 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2861. Min Act: -0.0005

Data Index: 914693 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3050. Min Act: -0.0005

Data Index: 357992 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3045. Min Act: -0.0005

Data Index: 543491 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2908. Min Act: -0.0005

Data Index: 1140739 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3089. Min Act: -0.0005

Data Index: 886661 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2846. Min Act: -0.0005

Data Index: 566355 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2930. Min Act: -0.0005

Data Index: 128855 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2812. Min Act: -0.0005

Data Index: 303414 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2659. Min Act: -0.0005

Data Index: 769834 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2836. Min Act: -0.0005

Data Index: 1245404 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2739. Min Act: -0.0005

Data Index: 845892 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2828. Min Act: -0.0005

Data Index: 359970 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2718. Min Act: -0.0005

Data Index: 297453 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2930. Min Act: -0.0005

Data Index: 1082389 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2798. Min Act: -0.0005

Data Index: 201559 (C4 (Web Text))

Max Activating Token Index: 993