Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3094 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1062. Min Act: -0.0001

Data Index: 587053 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1070. Min Act: -0.0002

Data Index: 339831 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1082677 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1292381 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0985. Min Act: -0.0001

Data Index: 240698 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0929. Min Act: -0.0001

Data Index: 592236 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0889. Min Act: -0.0001

Data Index: 759370 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0914. Min Act: -0.0001

Data Index: 632043 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0912. Min Act: -0.0002

Data Index: 30953 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0870. Min Act: -0.0002

Data Index: 863862 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1224204 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0929. Min Act: -0.0001

Data Index: 645761 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0808. Min Act: -0.0002

Data Index: 471851 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1265066 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0821. Min Act: -0.0002

Data Index: 444806 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0729. Min Act: -0.0002

Data Index: 565831 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1316325 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1544089 (Python Code)

Max Activating Token Index: 430

Text #18

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1018945 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0781. Min Act: -0.0001

Data Index: 609612 (C4 (Web Text))

Max Activating Token Index: 754