Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5125 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.8700. Min Act: -0.0000

Data Index: 1233786 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1049723 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.8104. Min Act: -0.0000

Data Index: 984840 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7917. Min Act: -0.0000

Data Index: 233221 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7082. Min Act: -0.0000

Data Index: 786638 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6739. Min Act: -0.0000

Data Index: 1070576 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.5409. Min Act: -0.0000

Data Index: 441354 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7201. Min Act: -0.0000

Data Index: 831978 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4658. Min Act: -0.0000

Data Index: 146245 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.5629. Min Act: -0.0000

Data Index: 585996 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1122638 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4776. Min Act: -0.0000

Data Index: 485455 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4904. Min Act: -0.0000

Data Index: 733590 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4169. Min Act: -0.0000

Data Index: 561996 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1068953 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3141. Min Act: -0.0000

Data Index: 14076 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3457. Min Act: -0.0000

Data Index: 1053068 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3799. Min Act: -0.0000

Data Index: 948455 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3975. Min Act: -0.0000

Data Index: 332781 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.2575. Min Act: -0.0000

Data Index: 819109 (C4 (Web Text))

Max Activating Token Index: 462